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

    Neuronpedia

    INDEX
    Explanations

    latex and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    becue
    0.42
     rápid
    0.37
     médiocrement
    0.37
     حديث
    0.36
     vaginale
    0.36
    ಯಲ್ಲಿ
    0.36
     aguas
    0.35
    হতের
    0.35
     ferrugineux
    0.35
     городской
    0.35
    POSITIVE LOGITS
     G
    0.35
     ブ
    0.31
    ojure
    0.31
     Com
    0.31
     L
    0.31
     C
    0.30
     开
    0.30
     O
    0.30
     g
    0.29
    rowadz
    0.29
    Act Density 0.001%

    No Known Activations