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

    Neuronpedia

    INDEX
    Explanations

    set of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saját
    1.14
    cych
    1.01
     Niet
    1.01
     Zd
    1.01
     menilai
    1.00
    ுங்கள்
    0.99
    ড
    0.99
     secteur
    0.99
     बर्खास्त
    0.99
    িণ
    0.97
    POSITIVE LOGITS
    idaknya
    2.06
    िंग्स
    2.02
    uptools
    1.78
    tee
    1.65
    ters
    1.63
    TING
    1.60
    tting
    1.53
    アップ
    1.46
    TINGS
    1.46
    jmp
    1.45
    Act Density 0.134%

    No Known Activations