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

    Neuronpedia

    INDEX
    Explanations

    entry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XIII
    -0.06
    jde
    -0.06
     tarz
    -0.06
    442
    -0.06
    icol
    -0.06
     ment
    -0.06
    νώ
    -0.06
     weg
    -0.06
    암
    -0.06
     bilgi
    -0.06
    POSITIVE LOGITS
    tweets
    0.07
    pendicular
    0.07
    Gov
    0.06
    iclass
    0.06
    _STRUCT
    0.06
     disponible
    0.06
    Square
    0.06
     dialogRef
    0.06
    Solution
    0.06
    phinx
    0.06
    Act Density 0.004%

    No Known Activations