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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or events involving people

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

    verbs followed by determiners/adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    المكان
    -0.45
    tawesome
    -0.40
     verschillen
    -0.39
     poffible
    -0.39
     nakalista
    -0.38
     neceſſ
    -0.38
     eſſ
    -0.38
     Romains
    -0.36
    COUVER
    -0.36
     samarbe
    -0.35
    POSITIVE LOGITS
    发表于
    0.56
    rungsseite
    0.49
    Personendaten
    0.44
     ddelweddau
    0.43
     puff
    0.41
    apimachinery
    0.41
    TagHelper
    0.41
     dilu
    0.41
     cad
    0.41
    \{\\
    0.40
    Act Density 0.102%

    No Known Activations