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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships

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

    family relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.83
    aarrggbb
    -0.75
     autorytatywna
    -0.65
    principalTable
    -0.64
    GOTREF
    -0.63
     zijne
    -0.63
    лтамалар
    -0.60
    tagHelperRunner
    -0.60
    ScopeManager
    -0.59
     queſta
    -0.57
    POSITIVE LOGITS
    <?
    0.33
    MathML
    0.31
    吃的
    0.29
     balles
    0.27
     نصف
    0.27
    Typed
    0.27
    UserScript
    0.27
     Gor
    0.26
     pressure
    0.26
     PRESSURE
    0.26
    Act Density 0.066%

    No Known Activations