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

    Neuronpedia

    INDEX
    Explanations

    perfectly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    افظ
    -0.07
    /false
    -0.07
    'T
    -0.07
    >";↵
    -0.07
    _End
    -0.07
    湿
    -0.07
    'em
    -0.07
     Usually
    -0.07
    (concat
    -0.06
     긴
    -0.06
    POSITIVE LOGITS
     perfectly
    0.16
     infinitely
    0.07
    lant
    0.07
    lick
    0.06
     ті
    0.06
     вполне
    0.06
    �
    0.06
     very
    0.06
     landmarks
    0.06
    ysts
    0.06
    Act Density 0.003%

    No Known Activations