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

    Neuronpedia

    INDEX
    Explanations

    personal choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .custom
    -0.07
     Duty
    -0.06
    revision
    -0.06
     justice
    -0.06
     discouraged
    -0.06
     분야
    -0.06
    圧
    -0.06
     Elaine
    -0.06
    міну
    -0.06
    FIXME
    -0.06
    POSITIVE LOGITS
     Spr
    0.06
    (transform
    0.06
    nob
    0.06
    bil
    0.06
     confirmPassword
    0.06
     수강
    0.06
    avorites
    0.06
     Aqu
    0.06
     UW
    0.06
     vim
    0.06
    Act Density 0.074%

    No Known Activations