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

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scalars
    -0.07
    шие
    -0.07
     Worse
    -0.06
     ks
    -0.06
     midst
    -0.06
    рист
    -0.06
     Const
    -0.06
    녕
    -0.06
    aret
    -0.06
     fy
    -0.06
    POSITIVE LOGITS
    发出
    0.06
     listing
    0.06
     kazanç
    0.06
     caffeine
    0.06
    postgresql
    0.06
    èn
    0.06
     благодаря
    0.06
    updating
    0.06
     fetisch
    0.06
    ائی
    0.06
    Act Density 0.004%

    No Known Activations