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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kylie
    -0.08
    Steve
    -0.08
    ige
    -0.08
    rne
    -0.07
    ์เน
    -0.07
     Vince
    -0.07
    เย
    -0.07
     ing
    -0.07
     Grove
    -0.07
    ge
    -0.07
    POSITIVE LOGITS
    or
    0.14
    AR
    0.14
    OR
    0.13
    ar
    0.12
    IR
    0.10
    ур
    0.09
    ur
    0.09
    ir
    0.09
    UR
    0.09
    zar
    0.09
    Act Density 0.460%

    No Known Activations