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

    Neuronpedia

    INDEX
    Explanations

    say "/"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fd
    -0.07
    iren
    -0.06
    attery
    -0.06
     Tale
    -0.06
    phi
    -0.06
     cname
    -0.06
    Š
    -0.06
    ReturnType
    -0.06
    扎
    -0.06
     [*
    -0.06
    POSITIVE LOGITS
    .lo
    0.07
     모
    0.06
    .Total
    0.06
    .ws
    0.06
    .image
    0.06
     Continental
    0.06
    .gr
    0.06
    waiting
    0.06
    ，该
    0.06
    alertView
    0.06
    Act Density 0.003%

    No Known Activations