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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise, exclamation, or emphasis

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

    exclamations of man or god

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    épendance
    -0.45
     ویکی‌پدی
    -0.45
     Polres
    -0.42
    tinyos
    -0.41
    utente
    -0.41
     tark
    -0.40
     sauve
    -0.39
    InputLabel
    -0.39
    öpf
    -0.39
     Investigaciones
    -0.37
    POSITIVE LOGITS
    Filmografie
    0.54
    MLLoader
    0.51
     poveznice
    0.49
    ViewFeatures
    0.46
    あー
    0.46
     JpaRepository
    0.44
    Diweddarwch
    0.44
    あぁ
    0.43
    цездатний
    0.42
     boy
    0.41
    Act Density 0.015%

    No Known Activations