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

    Neuronpedia

    INDEX
    Explanations

    conditional and auxiliary verbs indicating potential actions or decisions

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

    hypothetical outcomes and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.77
    ьаж
    -0.72
    elemField
    -0.71
    ftagPool
    -0.71
    GraphicsUnit
    -0.71
    المكان
    -0.70
    uxxxx
    -0.69
    principalColumn
    -0.69
    WriteTagHelper
    -0.68
    تقاوى
    -0.66
    POSITIVE LOGITS
     seguinte
    0.40
     wrote
    0.40
     instead
    0.37
    是这样的
    0.37
     folgender
    0.35
     writes
    0.34
    是这样
    0.34
     would
    0.34
     modified
    0.33
     write
    0.33
    Act Density 0.153%

    No Known Activations