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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating classification or categorization within specific headings or umbrellas

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

    under the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fís
    -0.33
    ồi
    -0.32
    verlauf
    -0.31
    tijd
    -0.30
    bestimmungen
    -0.30
     Replay
    -0.28
     قطع
    -0.28
    vergleich
    -0.28
     made
    -0.28
     very
    -0.28
    POSITIVE LOGITS
     autorytatywna
    1.09
     pinulongan
    0.92
    ValueStyle
    0.84
    AnchorStyles
    0.82
     under
    0.79
     resourceCulture
    0.79
    Under
    0.77
    PyExc
    0.76
     Wikimedijinoj
    0.75
    under
    0.75
    Act Density 0.027%

    No Known Activations