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

    Neuronpedia

    INDEX
    Explanations

    dare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    captcha
    -0.07
    选�
    -0.06
    ihanna
    -0.06
     Rihanna
    -0.06
     яв
    -0.06
     ifade
    -0.06
    肩
    -0.06
     Для
    -0.06
    ρίς
    -0.06
     ridden
    -0.06
    POSITIVE LOGITS
    are
    0.07
    .sum
    0.07
    family
    0.07
    ')↵↵
    0.07
    티
    0.07
    .join
    0.07
    etí
    0.06
    boarding
    0.06
    aire
    0.06
     once
    0.06
    Act Density 0.004%

    No Known Activations