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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to scientific or technical specifications

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

    Follows a question mark

    np_acts-logits-general · gemini-2.0-flash

    questions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.63
    MessageOf
    -0.54
     épo
    -0.54
    -
    -0.46
    featureID
    -0.46
     Chwiliwch
    -0.45
     of
    -0.43
    awtextra
    -0.43
    名叫
    -0.42
    fjspx
    -0.41
    POSITIVE LOGITS
     Majefty
    0.78
     Cæsar
    0.73
     armis
    0.73
    ppuden
    0.72
    WebServlet
    0.72
     itſelf
    0.72
     pleaſure
    0.67
     ſche
    0.66
     wikipagina
    0.66
    NgModule
    0.66
    Act Density 0.776%

    No Known Activations