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

    Neuronpedia

    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     буд
    -0.07
    ’h
    -0.07
     Ô
    -0.06
     Inst
    -0.06
    _create
    -0.06
    roads
    -0.06
     rozh
    -0.06
    _precision
    -0.06
     GLUT
    -0.06
     nues
    -0.06
    POSITIVE LOGITS
     площ
    0.07
    ие
    0.07
    _FORWARD
    0.06
    Denver
    0.06
    ΟΛΟΓ
    0.06
     println
    0.06
    理解
    0.06
    سام
    0.06
    bos
    0.06
     ALSO
    0.06
    Act Density 0.015%

    No Known Activations