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
    elan
    -0.07
     ähn
    -0.07
    ISTIC
    -0.07
     XY
    -0.06
    أربع
    -0.06
    砾
    -0.06
    磅
    -0.06
     descend
    -0.06
    HY
    -0.06
    踔
    -0.06
    POSITIVE LOGITS
    玩意
    0.08
    GI
    0.07
     Ruth
    0.07
    에서도
    0.07
    纪委
    0.07
     Bernie
    0.07
    طبيع
    0.07
    FIG
    0.07
    פיתוח
    0.07
    bish
    0.07
    Act Density 0.003%

    No Known Activations