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

    Neuronpedia

    INDEX
    Explanations

    acronyms and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     व्यापारी
    0.43
     Reliability
    0.42
     reliability
    0.38
    cena
    0.38
     ദ
    0.38
    ത്തേ
    0.38
    governmental
    0.37
    thebibliography
    0.36
    𝕡
    0.36
    Dinner
    0.36
    POSITIVE LOGITS
     Math
    0.43
    /
    0.40
     EL
    0.40
    ELO
    0.37
    SEL
    0.37
     W
    0.37
    EL
    0.36
    IDA
    0.36
    $.
    0.36
     exits
    0.36
    Act Density 0.000%

    No Known Activations