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

    Neuronpedia

    INDEX
    Explanations

    Email addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐎
    -0.08
    iscal
    -0.08
    gué
    -0.08
    تسويق
    -0.07
    ções
    -0.07
    ễn
    -0.07
    葫芦
    -0.07
    patible
    -0.07
    quip
    -0.07
     Christ
    -0.07
    POSITIVE LOGITS
     MediaType
    0.08
     MON
    0.07
    热线
    0.07
     Finding
    0.07
    .some
    0.07
    getWindow
    0.07
     словам
    0.07
     прием
    0.07
     HUD
    0.07
    <<"
    0.06
    Act Density 0.002%

    No Known Activations