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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()});↵
    -0.07
     dealers
    -0.07
     lg
    -0.06
     المو
    -0.06
    cial
    -0.06
    stants
    -0.06
     repercussions
    -0.06
     enh
    -0.06
    .Singleton
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     addresses
    0.07
    ุม
    0.06
    eed
    0.06
    ��
    0.06
     aliment
    0.06
    .sqrt
    0.06
    acic
    0.06
    ivement
    0.06
    _document
    0.06
    .correct
    0.06
    Act Density 0.004%

    No Known Activations