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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fetch
    -0.06
     베
    -0.06
     ap
    -0.06
     constr
    -0.06
    (Error
    -0.06
     lí
    -0.06
     vzpom
    -0.06
     Allocator
    -0.06
    (control
    -0.06
     SZ
    -0.06
    POSITIVE LOGITS
    cir
    0.06
    に向
    0.06
     mücadele
    0.06
    atility
    0.06
     موتور
    0.06
    -Mobile
    0.06
    agonal
    0.06
    lection
    0.06
    .content
    0.06
    centage
    0.06
    Act Density 0.010%

    No Known Activations