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

    Neuronpedia

    INDEX
    Explanations

    elements related to experimental methodology and results in scientific research

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

    Referring to figures or tables

    np_acts-logits-general · gemini-2.0-flash

    in figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.67
    ?
    -0.63
    Viitteet
    -0.49
    ?"
    -0.49
    Насе
    -0.47
    Билгалдахарш
    -0.47
    ubov
    -0.46
    canestro
    -0.44
     rec
    -0.44
    espn
    -0.43
    POSITIVE LOGITS
     Figure
    2.35
     Fig
    2.25
    Figure
    2.22
    Fig
    2.15
     Figs
    1.82
     figure
    1.80
    FIGURE
    1.79
    figure
    1.77
     FIGURE
    1.75
     Figures
    1.75
    Act Density 2.590%

    No Known Activations