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

    Neuronpedia

    INDEX
    Explanations

    af/fuck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shal
    -0.06
     더욱
    -0.06
    ethod
    -0.06
    ouncer
    -0.06
    MZ
    -0.06
    �ng
    -0.06
    .Guid
    -0.06
    .padding
    -0.05
    stories
    -0.05
    Touchable
    -0.05
    POSITIVE LOGITS
     Hur
    0.07
    ند
    0.07
    Hur
    0.07
     uncon
    0.07
     três
    0.07
     uns
    0.07
    工作
    0.07
     "]");↵
    0.07
     citizens
    0.07
     fret
    0.06
    Act Density 0.001%

    No Known Activations