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

    Neuronpedia

    INDEX
    Explanations

    style or creative ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aluminium
    -0.09
    _reason
    -0.08
     adel
    -0.08
    TMP
    -0.08
    医生
    -0.07
    =date
    -0.07
     traveling
    -0.07
     aprend
    -0.07
    优先
    -0.07
    =model
    -0.07
    POSITIVE LOGITS
     staggering
    0.07
    (NUM
    0.07
     zIndex
    0.07
     Больш
    0.07
    เอก
    0.06
    .realpath
    0.06
    扰
    0.06
    补充
    0.06
     ني
    0.06
    퉜
    0.06
    Act Density 0.154%

    No Known Activations