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

    Neuronpedia

    INDEX
    Explanations

    Escort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    秋
    -0.07
     秋
    -0.07
     Anime
    -0.07
     Bou
    -0.07
     Goth
    -0.07
     Completed
    -0.06
     hoops
    -0.06
    _Tick
    -0.06
    -Jul
    -0.06
    _oct
    -0.06
    POSITIVE LOGITS
    dıkları
    0.07
    سی
    0.06
     соверш
    0.06
     sp
    0.06
     yaptı
    0.06
     Jeremiah
    0.06
    لمات
    0.06
    .longitude
    0.06
    ():↵
    0.06
    .componentInstance
    0.06
    Act Density 0.025%

    No Known Activations