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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TV
    -0.07
     horas
    -0.07
     IRS
    -0.06
    bz
    -0.06
     AssertionError
    -0.06
     tween
    -0.06
    HTTPRequestOperation
    -0.06
     Закону
    -0.06
     Mö
    -0.06
    Bruce
    -0.06
    POSITIVE LOGITS
     paragraphs
    0.07
     fearless
    0.07
     قانون
    0.07
    (rep
    0.06
    (bitmap
    0.06
     unemployed
    0.06
     elektrik
    0.06
    (util
    0.06
    ько
    0.06
     frogs
    0.06
    Act Density 0.007%

    No Known Activations