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

    Neuronpedia

    INDEX
    Explanations

    symbols and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ない
    0.23
    oretically
    0.21
     puis
    0.20
    ногда
    0.19
    FixedHeight
    0.19
    ோ
    0.18
    лната
    0.18
    ർ
    0.18
    ść
    0.18
    vf
    0.18
    POSITIVE LOGITS
     мощности
    0.21
     gosto
    0.21
     actes
    0.20
     olan
    0.20
     oferty
    0.19
    $)$.
    0.19
     nati
    0.19
     tarixi
    0.19
    rela
    0.19
     των
    0.19
    Act Density 1.137%

    No Known Activations