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

    Neuronpedia

    INDEX
    Explanations

    alphabet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dennis
    -0.07
     creature
    -0.07
     Mik
    -0.07
     trở
    -0.06
    rms
    -0.06
     gatherings
    -0.06
     username
    -0.06
     Về
    -0.06
     piece
    -0.06
     Dar
    -0.06
    POSITIVE LOGITS
     alphabet
    0.07
    phabet
    0.06
    ?>↵↵
    0.06
     Alphabet
    0.06
     EG
    0.06
    (convert
    0.06
     HEX
    0.06
    ieval
    0.06
    AT
    0.06
     Burb
    0.06
    Act Density 0.005%

    No Known Activations