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

    Neuronpedia

    INDEX
    Explanations

    /values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝕂
    -0.07
    镋
    -0.07
    追赶
    -0.07
    urban
    -0.07
    姱
    -0.07
    ߎ
    -0.07
    扅
    -0.07
     misguided
    -0.07
    踟
    -0.07
     (*)(
    -0.07
    POSITIVE LOGITS
    roduced
    0.07
    ,this
    0.07
    PRESSION
    0.07
    溢
    0.07
     reasonable
    0.06
     disposed
    0.06
    用了
    0.06
    eof
    0.06
    	cs
    0.06
     _,
    0.06
    Act Density 0.002%

    No Known Activations