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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protested
    -0.07
     undertaking
    -0.07
    Producto
    -0.07
     pregnancy
    -0.06
    .FIELD
    -0.06
     Кар
    -0.06
    -born
    -0.06
     relax
    -0.06
    hift
    -0.06
    ні
    -0.06
    POSITIVE LOGITS
     doi
    0.07
     DRM
    0.07
    CRM
    0.07
     أن
    0.07
    ONY
    0.07
    leen
    0.06
    zure
    0.06
    .shop
    0.06
     liebe
    0.06
    .Cell
    0.06
    Act Density 0.464%

    No Known Activations