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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筹建
    -0.07
    zimmer
    -0.07
    ﲎ
    -0.07
    -0.07
    _open
    -0.07
    污水
    -0.07
    小康社会
    -0.07
    ,omitempty
    -0.07
    放开
    -0.07
     rms
    -0.07
    POSITIVE LOGITS
    ATERIAL
    0.07
     легко
    0.07
     forgiving
    0.06
     grade
    0.06
     Infant
    0.06
     confuse
    0.06
    oc
    0.06
    rics
    0.06
    rench
    0.06
    万物
    0.06
    Act Density 0.054%

    No Known Activations