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

    Neuronpedia

    INDEX
    Explanations

    phase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，大
    -0.06
    nehmen
    -0.06
     Sexo
    -0.06
     чуд
    -0.06
    butt
    -0.06
     Disneyland
    -0.06
    cv
    -0.06
    only
    -0.06
    acf
    -0.06
    _EQUALS
    -0.06
    POSITIVE LOGITS
    844
    0.08
    208
    0.07
    <Character
    0.07
    158
    0.06
    207
    0.06
     residing
    0.06
    etail
    0.06
    337
    0.06
    ;font
    0.06
     zone
    0.06
    Act Density 0.002%

    No Known Activations