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

    Neuronpedia

    INDEX
    Explanations

    Quotations and negations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    фик
    -0.07
     ga
    -0.07
    誌
    -0.06
    Heart
    -0.06
    	types
    -0.06
    дром
    -0.06
     ObjectType
    -0.06
     파일
    -0.06
     getColumn
    -0.06
    $num
    -0.06
    POSITIVE LOGITS
     HY
    0.07
    (mark
    0.07
     Pol
    0.07
     Орг
    0.07
     lodge
    0.06
    oce
    0.06
    .ff
    0.06
    ydro
    0.06
    .align
    0.06
    aupt
    0.06
    Act Density 0.014%

    No Known Activations