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

    Neuronpedia

    INDEX
    Explanations

    assertions and qualifiers related to validity and acceptability

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

    Preceding forms of "to be" (is, was, are, etc.)

    np_acts-logits-general · gemini-2.0-flash

    is not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     however
    -0.63
     же
    -0.57
     ovviamente
    -0.57
    Obviously
    -0.56
    によると
    -0.56
     obviously
    -0.55
     entanto
    -0.54
    сюда
    -0.54
    oso
    -0.53
     oczywiście
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    1.18
     فريبيس
    1.08
     المعيارى
    1.00
     Normdatei
    0.97
    bootstrapcdn
    0.94
    extAlignment
    0.94
     صوتيه
    0.94
    ScopeManager
    0.93
     ویکی‌پدیا
    0.91
     وتسجيلات
    0.91
    Act Density 0.743%

    No Known Activations