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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and expressions of uncertainty or inquiry

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

    phrase punctuation and short words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.69
    EndInit
    -0.63
    AutoresizingMask
    -0.55
    FormTagHelper
    -0.51
    HtmlAttribute
    -0.50
     AssemblyTitle
    -0.49
     ModelExpression
    -0.49
    🖨
    -0.48
    rawDesc
    -0.48
    LabelTagHelper
    -0.48
    POSITIVE LOGITS
     lack
    0.40
    Референце
    0.36
     economy
    0.36
     adv
    0.33
     flood
    0.33
     sy
    0.33
    }")]
    0.32
    œ
    0.32
    во
    0.32
     suggestion
    0.31
    Act Density 0.094%

    No Known Activations