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

    Neuronpedia

    INDEX
    Explanations

    OPTIONS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dudley
    -0.06
    “For
    -0.06
     LAT
    -0.06
    WEB
    -0.06
     čer
    -0.06
     getMenuInflater
    -0.06
     aggression
    -0.06
    “As
    -0.06
     Sher
    -0.06
     Lew
    -0.06
    POSITIVE LOGITS
    (ignore
    0.07
     MOCK
    0.07
     ethics
    0.07
    .cont
    0.07
    .eth
    0.07
    slice
    0.07
     uniforms
    0.06
     خطر
    0.06
    ﾉ
    0.06
    .layers
    0.06
    Act Density 0.000%

    No Known Activations