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

    Neuronpedia

    INDEX
    Explanations

    references to verification or assessment processes

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

    checks and verification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    listdir
    -0.44
    |
    -0.40
     pprint
    -0.39
     Picchu
    -0.39
    anager
    -0.38
     CreateTagHelper
    -0.37
    出版年
    -0.36
     Leopold
    -0.36
     Password
    -0.36
     Porphy
    -0.36
    POSITIVE LOGITS
    Checks
    1.59
     Checks
    1.59
     checks
    1.58
    checks
    1.54
     cheques
    0.93
    checking
    0.86
    Checking
    0.81
     Checking
    0.79
     checking
    0.70
    CloseOperation
    0.64
    Act Density 0.008%

    No Known Activations