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

    Neuronpedia

    INDEX
    Explanations

    references to figures and visual data representations within the document

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

    references to figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.51
    HDL
    -0.48
     nakalista
    -0.47
    évaluateur
    -0.47
     дописавши
    -0.46
    GTCX
    -0.46
     pinulongan
    -0.46
    SBATCH
    -0.46
     kaarangay
    -0.45
     PCL
    -0.45
    POSITIVE LOGITS
     figure
    1.48
     figures
    1.26
     Figure
    1.26
    figure
    1.24
     Figures
    1.20
    Figure
    1.19
    Figures
    1.11
     FIGURES
    1.09
    figures
    1.05
     FIGURE
    1.03
    Act Density 0.138%

    No Known Activations