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

    Neuronpedia

    INDEX
    Explanations

    efficiency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Line
    -0.07
    Spatial
    -0.06
    Dict
    -0.06
     Venez
    -0.06
     jobject
    -0.06
     fiberglass
    -0.06
    _mb
    -0.06
    ;line
    -0.06
    .proj
    -0.06
    /game
    -0.06
    POSITIVE LOGITS
     Electoral
    0.07
     muchos
    0.07
     �
    0.06
     Sakura
    0.06
    edor
    0.06
     happy
    0.06
     plusieurs
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
     covering
    0.06
    .General
    0.06
    Act Density 0.014%

    No Known Activations