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

    Neuronpedia

    INDEX
    Explanations

    references or comparisons to other things or concepts

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

    and the like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
     utafitiHapana
    -0.81
    Autoritní
    -0.77
     kasarigan
    -0.76
    iſen
    -0.71
    ロウィン
    -0.70
    providedIn
    -0.69
    AndroidJUnit
    -0.69
    <unused3>
    -0.69
    <unused42>
    -0.69
    POSITIVE LOGITS
    ,
    0.41
    TextBoxColumn
    0.39
    ;
    0.37
     would
    0.35
    ViewInit
    0.34
    Altro
    0.33
     (
    0.32
    Sonstiges
    0.32
     peu
    0.31
     $\
    0.29
    Act Density 0.008%

    No Known Activations