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

    Neuronpedia

    INDEX
    Explanations

    intimate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thead
    -0.07
     kontro
    -0.06
    alyzer
    -0.06
     лист
    -0.06
     SimpleName
    -0.06
     colour
    -0.06
     ultrasound
    -0.06
     シ
    -0.06
    жд
    -0.06
    _tail
    -0.06
    POSITIVE LOGITS
    —that
    0.08
     millennials
    0.07
    sey
    0.07
    );↵↵↵↵
    0.07
    }")↵↵
    0.06
    gewater
    0.06
     Chic
    0.06
    hips
    0.06
     rave
    0.06
    (bool
    0.06
    Act Density 0.009%

    No Known Activations