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

    Neuronpedia

    INDEX
    Explanations

    code comments and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.48
    acen
    0.47
    -
    0.46
    (-
    0.46
    Unit
    0.44
    Servo
    0.44
    an
    0.44
    қ
    0.43
    ان
    0.43
    Clark
    0.43
    POSITIVE LOGITS
    ...*/
    0.82
     }*/
    0.53
     Removes
    0.52
    }*/
    0.49
     Smartphones
    0.48
     */
    0.46
    jshint
    0.46
     Eliminate
    0.46
     Goodbye
    0.46
     flamboyant
    0.46
    Act Density 0.002%

    No Known Activations