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

    Neuronpedia

    INDEX
    Explanations

    declarations of data types in programming

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

    variable types and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verifyException
    -0.57
    fjspx
    -0.56
    AccessorTable
    -0.56
    matchCondition
    -0.51
    awtextra
    -0.51
    saraba
    -0.49
    SequentialGroup
    -0.48
    TestTools
    -0.47
     OMITBAD
    -0.47
     createSlice
    -0.45
    POSITIVE LOGITS
    Manually
    0.42
     Manually
    0.40
    phorbia
    0.40
     Alquiler
    0.38
    Constructors
    0.38
    السكان
    0.37
     chitarra
    0.36
     lavoratori
    0.36
     doccia
    0.36
     Whelan
    0.36
    Act Density 0.004%

    No Known Activations