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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their associated actions or conditions

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

    Comes after "Can" or "to"

    np_acts-logits-general · gemini-2.0-flash

    ability to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     melap
    -0.48
     Bedür
    -0.45
     pemuda
    -0.45
     ideen
    -0.44
     memerlukan
    -0.44
     mencu
    -0.43
     zmieni
    -0.43
     Głów
    -0.43
     pungkas
    -0.42
     spørs
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.72
    OGND
    0.68
    ⟬
    0.65
     nakalista
    0.60
    RTEX
    0.58
     PTT
    0.58
    WireFormatLite
    0.58
    expandindo
    0.56
    Rüyada
    0.55
     fly
    0.55
    Act Density 0.544%

    No Known Activations