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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ость
    -0.08
    ишь
    -0.07
    Ь
    -0.07
     жизнь
    -0.07
    苦笑
    -0.07
    低头
    -0.06
    (comm
    -0.06
    开玩笑
    -0.06
    .are
    -0.06
     принял
    -0.06
    POSITIVE LOGITS
    뗏
    0.07
    解
    0.07
     gaining
    0.06
    _OFFSET
    0.06
    延迟
    0.06
    element
    0.06
    isdigit
    0.06
    _supported
    0.06
    看点
    0.06
    })
    0.06
    Act Density 0.010%

    No Known Activations