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

    Neuronpedia

    INDEX
    Explanations

    expressions of social expectations and judgments

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

    self-respecting andno reasonable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WAVE
    -0.34
     Wave
    -0.30
     valg
    -0.29
     GENTLE
    -0.28
    <sup>
    -0.27
    NVIC
    -0.27
    dlg
    -0.27
    Oat
    -0.27
     relais
    -0.27
     pié
    -0.26
    POSITIVE LOGITS
    rungsseite
    0.85
     Савезне
    0.78
    parsedMessage
    0.73
    LookAnd
    0.71
    ⤹
    0.70
     noDo
    0.68
    expandindo
    0.67
     CreateTagHelper
    0.67
     Jefus
    0.66
    fromnode
    0.66
    Act Density 0.041%

    No Known Activations