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

    Neuronpedia

    INDEX
    Explanations

    connections between various factors in empirical studies

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

    relation between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.80
    WriteTagHelper
    -0.73
    BufferException
    -0.71
     initComponents
    -0.69
     للاسماء
    -0.68
    UserScript
    -0.66
    الحياه
    -0.66
    setVerticalGroup
    -0.65
     חיצוניים
    -0.65
     imagui
    -0.64
    POSITIVE LOGITS
     related
    0.37
     relation
    0.36
     corresponding
    0.34
     Related
    0.32
     relationship
    0.32
     associated
    0.31
    related
    0.31
    关联
    0.30
     Corruption
    0.28
     pè
    0.28
    Act Density 0.105%

    No Known Activations