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

    Neuronpedia

    INDEX
    Explanations

    Java keywords and class structures in code snippets

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

    Code, database, or technical names

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.46
     Your
    -0.42
     though
    -0.39
    וני
    -0.39
     sch
    -0.39
     ber
    -0.37
    inck
    -0.37
    fillStyle
    -0.37
     rés
    -0.37
     [
    -0.37
    POSITIVE LOGITS
    ::
    1.20
    ItemBackground
    0.93
    ::_('
    0.88
    ControllerAdvice
    0.85
    ArrowToggle
    0.82
    featureID
    0.77
    ::__
    0.74
     ::
    0.74
     فريبيس
    0.74
    ::_
    0.69
    Act Density 0.331%

    No Known Activations