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

    Neuronpedia

    INDEX
    Explanations

    rophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('=
    -0.07
    -selection
    -0.07
     Shooting
    -0.06
     presentation
    -0.06
    الا
    -0.06
     urgent
    -0.06
    你的
    -0.06
     start
    -0.06
     feeling
    -0.06
     ulus
    -0.06
    POSITIVE LOGITS
    Integer
    0.07
     grup
    0.07
    vič
    0.07
    B
    0.06
     önemli
    0.06
    兰
    0.06
     Valle
    0.06
     This
    0.06
    ub
    0.06
     Vi
    0.06
    Act Density 0.000%

    No Known Activations