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

    Neuronpedia

    INDEX
    Explanations

    not seeing something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -text
    -0.07
     giữa
    -0.07
     explained
    -0.07
    studio
    -0.07
    pie
    -0.06
    (pc
    -0.06
     ecosystem
    -0.06
     literary
    -0.06
    окумент
    -0.06
    絜
    -0.06
    POSITIVE LOGITS
     만나
    0.07
    电机
    0.07
    눋
    0.07
     MULTI
    0.07
    헨
    0.07
    骨
    0.07
     libs
    0.06
    .NotNull
    0.06
     Fn
    0.06
     stabilization
    0.06
    Act Density 0.019%

    No Known Activations