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

    Neuronpedia

    INDEX
    Explanations

    statements about expectations and accountability in various contexts

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

    Expected tokens or what to expect

    np_acts-logits-general · gemini-2.0-flash

    expect this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.72
    InitVars
    -0.66
     صوتيه
    -0.63
    DebuggerNonUser
    -0.62
    webElementXpaths
    -0.59
    expandindo
    -0.58
     يتيمه
    -0.57
     ModelExpression
    -0.56
     SwiftUI
    -0.56
    AutoScaleMode
    -0.55
    POSITIVE LOGITS
     from
    0.97
    จาก
    0.77
    from
    0.74
     από
    0.68
    From
    0.64
     FROM
    0.63
     dari
    0.62
     kutoka
    0.61
     expecting
    0.61
    出自
    0.59
    Act Density 0.205%

    No Known Activations