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

    Neuronpedia

    INDEX
    Explanations

    Criticism and giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    regions
    -0.07
     Dust
    -0.07
    inating
    -0.06
    ification
    -0.06
    fic
    -0.06
     Swagger
    -0.06
    cano
    -0.06
    nu
    -0.06
     Asus
    -0.06
     hist
    -0.06
    POSITIVE LOGITS
     empez
    0.07
     зробити
    0.07
    avez
    0.06
    [K
    0.06
     ~~
    0.06
     tegen
    0.06
    ělí
    0.06
    (Duration
    0.06
    GetProcAddress
    0.06
     Yorkshire
    0.06
    Act Density 0.244%

    No Known Activations