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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters in code structures

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

    code blocks and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.75
     Majefty
    -0.74
     Chriftian
    -0.71
     Monfieur
    -0.69
     houſe
    -0.68
     Diſ
    -0.65
     ſtre
    -0.65
     itſelf
    -0.64
     myſelf
    -0.64
     Houſe
    -0.63
    POSITIVE LOGITS
     Nadel
    0.40
     للمعارف
    0.39
    一番
    0.37
    jada
    0.36
    Linda
    0.36
    pars
    0.35
     ProtoMessage
    0.35
    ARB
    0.35
    oneofs
    0.35
    kuma
    0.35
    Act Density 0.116%

    No Known Activations