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

    Neuronpedia

    INDEX
    Explanations

    References to pages/chapters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     watches
    -0.07
     phố
    -0.07
    igo
    -0.06
    Bloc
    -0.06
     doğru
    -0.06
    velte
    -0.06
     �
    -0.06
    ()){
    -0.06
    جد
    -0.06
     disposit
    -0.06
    POSITIVE LOGITS
    READING
    0.08
     genomic
    0.06
    дина
    0.06
     Sy
    0.06
    ozo
    0.06
    트
    0.06
     normalize
    0.06
    graduate
    0.06
    основ
    0.06
    _dom
    0.06
    Act Density 0.014%

    No Known Activations