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

    Neuronpedia

    INDEX
    Explanations

    buildings/properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     auc
    -0.07
     dagen
    -0.07
    Sparse
    -0.07
     tedious
    -0.07
    어요
    -0.06
     map
    -0.06
    食べ
    -0.06
     platform
    -0.06
    比賽
    -0.06
     tourists
    -0.06
    POSITIVE LOGITS
    ccak
    0.07
    ꒳
    0.07
    kubectl
    0.07
     FontWeight
    0.07
     Lowest
    0.07
    踵
    0.07
     kèm
    0.07
    咥
    0.07
    沇
    0.06
     بصورة
    0.06
    Act Density 0.029%

    No Known Activations