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

    Neuronpedia

    INDEX
    Explanations

    instances of conflict or resistance, particularly in high-stress situations

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

    resisting arrest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     åren
    -0.37
     potrà
    -0.33
     демо
    -0.32
    лос
    -0.31
     ledig
    -0.31
     pourrez
    -0.31
    放
    -0.31
     estaremos
    -0.30
    WriteAttribute
    -0.30
    HttpFoundation
    -0.30
    POSITIVE LOGITS
     nakalista
    0.60
     MainAxisSize
    0.59
     للاسماء
    0.57
    VIAF
    0.57
     nahilalakip
    0.54
     ब्रेकडाउन
    0.54
     ujednoznacz
    0.52
    tagHelperRunner
    0.51
    MessageTagHelper
    0.50
    $​
    0.48
    Act Density 0.018%

    No Known Activations