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

    Neuronpedia

    INDEX
    Explanations

    terms related to cookies and digital privacy policies

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

    types of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.79
     للاسماء
    -0.78
     snippetHide
    -0.76
     ProtoMessage
    -0.76
    isContained
    -0.76
     ModelExpression
    -0.75
     queſta
    -0.75
    UnsafeEnabled
    -0.73
     ſeiner
    -0.73
     ſeine
    -0.72
    POSITIVE LOGITS
    Category
    0.39
    category
    0.36
    types
    0.34
    type
    0.33
    ByType
    0.33
    ↵↵↵
    0.33
    ↵↵
    0.32
     Verkehrs
    0.31
    Type
    0.31
    ,
    0.31
    Act Density 0.472%

    No Known Activations