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

    Neuronpedia

    INDEX
    Explanations

    second-person pronouns and related verbs indicating action or interaction

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

    you or ye followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sicht
    -0.34
    今回は
    -0.34
     Dinge
    -0.33
     platform
    -0.31
     hilos
    -0.31
     sewa
    -0.31
     modalità
    -0.31
     Pläne
    -0.30
     duradero
    -0.30
     initial
    -0.30
    POSITIVE LOGITS
    SequentialGroup
    0.65
    AddTagHelper
    0.64
     مرئيه
    0.60
     تضيفلها
    0.59
    ConstraintMaker
    0.58
    󠁣
    0.57
    0.57
     témoig
    0.56
     мәкал
    0.56
    encils
    0.56
    Act Density 0.034%

    No Known Activations