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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing actions or conditions related to receiving or obtaining something

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

    Japanese text

    np_acts-logits-general · gemini-2.0-flash

    Japanese and Spanish verbs, English past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Añade
    -0.60
     وين
    -0.57
     spoken
    -0.55
    written
    -0.53
     fazem
    -0.53
     hablan
    -0.53
     juegan
    -0.53
     llegan
    -0.52
     ويت
    -0.52
    poken
    -0.51
    POSITIVE LOGITS
     was
    1.80
     took
    1.77
     went
    1.67
     did
    1.65
     gave
    1.62
     came
    1.55
     didn
    1.48
     became
    1.47
     began
    1.44
    took
    1.42
    Act Density 0.054%

    No Known Activations