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

    Neuronpedia

    INDEX
    Explanations

    Power outlets and chargers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    都是
    -0.07
    rx
    -0.07
     equality
    -0.07
    لاح
    -0.06
    lus
    -0.06
    िव
    -0.06
    rw
    -0.06
    _Speed
    -0.06
     переб
    -0.06
    iol
    -0.06
    POSITIVE LOGITS
    *Math
    0.08
    .Creator
    0.06
     Empresa
    0.06
     Desert
    0.06
    _builtin
    0.06
    äche
    0.06
     خوش
    0.06
     демон
    0.06
     descricao
    0.06
    trainer
    0.06
    Act Density 0.133%

    No Known Activations