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

    Neuronpedia

    INDEX
    Explanations

    programming or coding-related terms and actions

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

    iterative technique, keep track, focusing your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.54
    XmlAccessType
    -0.53
    agisse
    -0.50
    -0.49
    WithIOException
    -0.48
    twimg
    -0.46
     MainAxisSize
    -0.43
    -------------</
    -0.43
     <=",
    -0.43
    ScopeManager
    -0.43
    POSITIVE LOGITS
    /*
    0.38
     depre
    0.38
    maru
    0.37
    dinga
    0.37
    Tail
    0.37
    المكان
    0.37
     domo
    0.36
    gridy
    0.36
    layers
    0.35
     Peas
    0.35
    Act Density 0.080%

    No Known Activations