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

    Neuronpedia

    INDEX
    Explanations

    references to figures and citations related to scientific data or technical specifications

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

    abbreviations like Inc, Ltd, FIG, Aug, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dieſe
    -0.73
     nahilalakip
    -0.73
    <unused14>
    -0.73
    [@BOS@]
    -0.73
    <unused8>
    -0.73
    <unused41>
    -0.72
    <unused51>
    -0.72
    <unused28>
    -0.72
    <unused16>
    -0.72
    <unused23>
    -0.72
    POSITIVE LOGITS
    BeginInit
    0.33
     dintr
    0.31
    <!--[
    0.29
    hånd
    0.28
     fotográfica
    0.27
     müm
    0.27
     rôles
    0.26
     czł
    0.26
     isInitialized
    0.26
     artístico
    0.25
    Act Density 0.232%

    No Known Activations