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

    Neuronpedia

    INDEX
    Explanations

    DOI identifiers and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mates
    0.71
     resources
    0.69
     papers
    0.68
     قرار
    0.68
     embedded
    0.68
    put
    0.67
    Permalink
    0.67
    屜
    0.67
     mise
    0.67
     show
    0.66
    POSITIVE LOGITS
    ∕
    1.33
     /(\
    1.18
    ／
    1.12
     /
    1.11
     ／
    1.09
    /
    1.05
    \/
    1.05
     /$
    1.03
    ⟋
    1.00
    /(
    1.00
    Act Density 0.009%

    No Known Activations