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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting symbols

    oai_token-act-pair · gemini-2.0-flash

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.66
     su
    -0.60
     $\
    -0.60
     R
    -0.58
     r
    -0.57
     p
    -0.56
     top
    -0.55
     n
    -0.50
     ha
    -0.49
     w
    -0.49
    POSITIVE LOGITS
     Efq
    0.91
     iſt
    0.91
     purpoſe
    0.86
     onCancelled
    0.85
     Waray
    0.85
     Monfieur
    0.85
     Shakspeare
    0.84
     незавершена
    0.84
     MainAxisSize
    0.84
     diſt
    0.82
    Act Density 1.134%

    No Known Activations