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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    去看
    -0.09
    .tc
    -0.07
    止め
    -0.07
    雩
    -0.07
    皿
    -0.06
    ascii
    -0.06
    溍
    -0.06
     alb
    -0.06
    הבנה
    -0.06
    altı
    -0.06
    POSITIVE LOGITS
     Dorm
    0.07
     Playlist
    0.07
     guid
    0.07
    Ợ
    0.07
    ophil
    0.07
    쬐
    0.07
    ened
    0.07
     pressure
    0.07
    Ğ
    0.07
    riter
    0.07
    Act Density 0.267%

    No Known Activations