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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bureaucracy
    -0.07
    ;r
    -0.07
    נושא
    -0.07
    (light
    -0.07
    rng
    -0.07
    出入
    -0.07
    _BLUE
    -0.07
     centerX
    -0.07
     dove
    -0.07
    ër
    -0.07
    POSITIVE LOGITS
     bày
    0.07
    esis
    0.07
    常委
    0.06
    หลาก
    0.06
     כפי
    0.06
    其
    0.06
     언
    0.06
     Paras
    0.06
    瞬
    0.06
     Dmit
    0.06
    Act Density 0.126%

    No Known Activations