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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to medical procedures and their potential effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets and URLs

    np_acts-logits-general · gemini-2.0-flash

    code comments and timestamps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iſt
    -0.98
     photolibrary
    -0.95
     ſch
    -0.94
     ſind
    -0.92
     myſelf
    -0.91
     Efq
    -0.90
    ſelf
    -0.89
     ſta
    -0.89
     itſelf
    -0.88
     ẞ
    -0.86
    POSITIVE LOGITS
     ,
    1.01
     of
    0.97
     and
    0.92
    ↵↵
    0.85
     .
    0.81
     to
    0.80
     -
    0.77
    and
    0.77
     is
    0.76
     a
    0.76
    Act Density 0.307%

    No Known Activations