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

    Neuronpedia

    INDEX
    Explanations

    identifiers and variable names in code snippets

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

    member variable prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁴
    -0.49
     Numerade
    -0.47
     redenen
    -0.39
     solidarité
    -0.38
    SpringBootTest
    -0.37
     avoient
    -0.36
     suaminya
    -0.36
     jongen
    -0.36
     pleaſure
    -0.36
     Begleitung
    -0.36
    POSITIVE LOGITS
     ErrInvalid
    0.58
    ValueStyle
    0.57
    hels
    0.53
     pseudo
    0.52
    WEBPACK
    0.52
    APORE
    0.52
     localObject
    0.52
     masking
    0.51
     nominal
    0.50
     preg
    0.50
    Act Density 0.014%

    No Known Activations