Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical or programming expressions involving variables and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical expressions with "+", "-", "\", or "frac"

    np_acts-logits-general · gemini-2.0-flash

    counting or numeric operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.50
    äsenti
    -0.49
     hurt
    -0.46
    aney
    -0.45
     Hit
    -0.44
     ear
    -0.44
    arro
    -0.44
     AppCompatTheme
    -0.44
     timeval
    -0.44
    ény
    -0.43
    POSITIVE LOGITS
    sidemargin
    0.88
    sizeCache
    0.83
     Chwiliwch
    0.81
    DataMember
    0.80
    protoimpl
    0.71
     estekak
    0.68
     <>",
    0.67
    SourceChecksum
    0.67
     незавершена
    0.66
    ConstraintMaker
    0.65
    Act Density 0.352%

    No Known Activations