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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (input
    -0.07
    ract
    -0.06
    istributions
    -0.06
     US
    -0.06
     shoe
    -0.06
    ımız
    -0.06
    307
    -0.06
     nghị
    -0.06
     EVENT
    -0.06
    966
    -0.06
    POSITIVE LOGITS
     Miche
    0.07
    ;amp
    0.07
    верж
    0.07
     manus
    0.06
     jurors
    0.06
    .EventSystems
    0.06
    ानम
    0.06
    ‌دان
    0.06
     erotische
    0.06
     tore
    0.06
    Act Density 0.039%

    No Known Activations