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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Move
    -0.07
     Far
    -0.06
     Gui
    -0.06
    hold
    -0.06
    outlined
    -0.06
    _W
    -0.06
    مارات
    -0.06
     Album
    -0.06
    #================================================================
    -0.06
     Mehmet
    -0.06
    POSITIVE LOGITS
     odom
    0.06
     percentile
    0.06
    ｿ
    0.06
    Runtime
    0.06
     debunk
    0.06
    itioner
    0.06
     regs
    0.06
     modulation
    0.06
     obscene
    0.06
     Comey
    0.06
    Act Density 0.002%

    No Known Activations