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

    Neuronpedia

    INDEX
    Explanations

    programming-related event arguments in code

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

    code, technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.33
     noqa
    -0.29
     право
    -0.28
     अलावा
    -0.27
    $
    -0.26
    ذ
    -0.26
     kaarangay
    -0.26
     unbekannt
    -0.25
     ويكيپيديا
    -0.25
    {:
    -0.24
    POSITIVE LOGITS
     témoig
    0.81
    stdio
    0.77
    ſcher
    0.76
    iſchen
    0.75
    iſen
    0.74
    niſſe
    0.74
    iſten
    0.70
    ロウィン
    0.69
    <unused17>
    0.69
    <unused51>
    0.69
    Act Density 0.000%

    No Known Activations