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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and expressions of perception

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

    seeing or hearing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OkHttpClient
    -0.52
    MessageOf
    -0.50
    XtraReports
    -0.49
    ondissement
    -0.49
     passphrase
    -0.48
    __',
    -0.48
    errHandler
    -0.47
    brtc
    -0.46
    RegressionTest
    -0.46
    rollup
    -0.46
    POSITIVE LOGITS
    Seeing
    0.50
     seeing
    0.50
     Seeing
    0.44
    saw
    0.41
    findpost
    0.40
     désolés
    0.40
     saw
    0.39
    Rüyada
    0.39
     widok
    0.38
     دیدن
    0.38
    Act Density 0.018%

    No Known Activations