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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fans
    -0.08
     flu
    -0.08
    よう
    -0.06
     favorite
    -0.06
     presidential
    -0.06
     bloom
    -0.06
     all
    -0.06
     Rotation
    -0.06
     visto
    -0.06
    oley
    -0.06
    POSITIVE LOGITS
    Contours
    0.08
    olution
    0.06
    аю
    0.06
    .Navigate
    0.06
     стос
    0.06
    .ObjectMeta
    0.06
    ешь
    0.06
     formas
    0.06
    usuarios
    0.06
    Prices
    0.06
    Act Density 0.000%

    No Known Activations