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

    Neuronpedia

    INDEX
    Explanations

    mov

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    енд
    -0.07
    zech
    -0.07
    _door
    -0.07
    .Mutex
    -0.07
    писан
    -0.06
    ضم
    -0.06
    啧
    -0.06
    UInt
    -0.06
    ßerdem
    -0.06
    udiant
    -0.06
    POSITIVE LOGITS
    nw
    0.07
    max
    0.07
     coral
    0.06
    曲
    0.06
    潤
    0.06
    .Mon
    0.06
    Notice
    0.06
     hạnh
    0.06
     }↵↵
    0.06
     tracing
    0.06
    Act Density 0.012%

    No Known Activations