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

    Neuronpedia

    INDEX
    Explanations

    high-frequency words and phrases that indicate existence or state of being

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

    is followed by adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.53
    StructEnd
    -0.52
    retudo
    -0.51
    Personendaten
    -0.51
     Geſ
    -0.50
    bibinfo
    -0.49
     čierna
    -0.48
     Verſ
    -0.48
     itſelf
    -0.48
    aarrggbb
    -0.48
    POSITIVE LOGITS
    hole
    0.36
     Hole
    0.35
    ConstraintMaker
    0.35
     Dux
    0.34
    новниш
    0.33
     HOLE
    0.32
    bl
    0.31
    webElementXpaths
    0.30
    Hole
    0.30
    方才
    0.30
    Act Density 0.152%

    No Known Activations