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

    Neuronpedia

    INDEX
    Explanations

    words related to actions, experiences, and organizations

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

    business or company descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.39
     Widerspruch
    -0.30
     Einfluß
    -0.30
     Zugang
    -0.29
     twij
    -0.28
     ușor
    -0.27
     bouteilles
    -0.26
     Voraussetzungen
    -0.26
     rodillas
    -0.26
    voorbeeld
    -0.26
    POSITIVE LOGITS
     فريبيس
    0.76
    niſſe
    0.69
     catering
    0.63
    <unused14>
    0.63
    <unused28>
    0.63
    <unused23>
    0.63
    <unused41>
    0.63
    <unused74>
    0.63
    <pad>
    0.63
    <unused3>
    0.63
    Act Density 0.043%

    No Known Activations