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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entire
    -0.07
    огод
    -0.07
     Others
    -0.07
    .tell
    -0.07
     twelve
    -0.06
    fir
    -0.06
    他們
    -0.06
    _week
    -0.06
    ingle
    -0.06
    자가
    -0.06
    POSITIVE LOGITS
    #ad
    0.07
    یشن
    0.06
     Mining
    0.06
    扩
    0.06
    _SDK
    0.06
    509
    0.06
     vector
    0.06
    .train
    0.06
    opsis
    0.06
     edu
    0.06
    Act Density 0.022%

    No Known Activations