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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _latency
    -0.06
    anity
    -0.06
     R
    -0.06
    owers
    -0.06
    rompt
    -0.06
    Wood
    -0.06
    ์พ
    -0.06
     oz
    -0.06
    ph
    -0.06
    	change
    -0.06
    POSITIVE LOGITS
     MODULE
    0.06
     особ
    0.06
    يل
    0.06
    Ｅ
    0.06
     ​​​
    0.06
     friendships
    0.06
    AGAIN
    0.06
     odstran
    0.06
     طی
    0.06
    SKTOP
    0.06
    Act Density 0.019%

    No Known Activations