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

    Neuronpedia

    INDEX
    Explanations

    RON

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jeep
    -0.07
    ="")↵
    -0.07
    られて
    -0.07
    laps
    -0.07
    日消息
    -0.07
    曝
    -0.07
    _vect
    -0.07
    _supported
    -0.07
    .Strings
    -0.06
    ElementType
    -0.06
    POSITIVE LOGITS
     Hall
    0.07
     ownership
    0.07
    (units
    0.07
    은
    0.07
     Vision
    0.07
    ˂
    0.06
    良
    0.06
    增量
    0.06
     بن
    0.06
    하는
    0.06
    Act Density 0.002%

    No Known Activations