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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     norm
    -0.07
     confessed
    -0.07
    完了
    -0.07
    خرو
    -0.07
    orie
    -0.07
    _combo
    -0.07
     psychotic
    -0.06
    .mac
    -0.06
    fé
    -0.06
    inals
    -0.06
    POSITIVE LOGITS
    -fill
    0.07
     ESL
    0.07
    -headed
    0.07
    /memory
    0.07
    生产商
    0.07
    加深
    0.07
    LC
    0.06
    sink
    0.06
    .room
    0.06
     infring
    0.06
    Act Density 0.000%

    No Known Activations