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

    Neuronpedia

    INDEX
    Explanations

    package installation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тов
    -0.07
    Camera
    -0.07
     가능한
    -0.06
     khỏi
    -0.06
    われる
    -0.06
    ovation
    -0.06
    ovky
    -0.06
    *</
    -0.06
    224
    -0.06
     possibly
    -0.06
    POSITIVE LOGITS
     Svens
    0.07
     Clem
    0.06
     λέ
    0.06
     TIM
    0.06
     předsed
    0.06
     lem
    0.06
     Jesus
    0.06
     trusting
    0.06
     lev
    0.06
     yaşan
    0.06
    Act Density 0.014%

    No Known Activations