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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .
    -0.61
     to
    -0.54
     or
    -0.49
     “
    -0.48
    </em>
    -0.47
    op
    -0.46
     quite
    -0.46
     которому
    -0.45
     ‘
    -0.45
    el
    -0.45
    POSITIVE LOGITS
    ^(@)
    0.94
     itſelf
    0.80
     photolibrary
    0.79
     Forumite
    0.79
     themſelves
    0.78
     fince
    0.77
     \\
    0.75
    felves
    0.75
    $")
    0.74
     Moslem
    0.73
    Act Density 0.671%

    No Known Activations