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

    Neuronpedia

    INDEX
    Explanations

    Alive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pointed
    -0.09
     don
    -0.08
     August
    -0.07
    $k
    -0.07
     fac
    -0.07
    or
    -0.07
    	assertThat
    -0.07
    ن
    -0.07
     wanting
    -0.07
     kategor
    -0.07
    POSITIVE LOGITS
     alive
    0.10
     Alive
    0.09
    Alive
    0.07
    wie
    0.07
    비스
    0.07
    _All
    0.06
     행복
    0.06
     đình
    0.06
    èo
    0.06
     Sunrise
    0.06
    Act Density 0.008%

    No Known Activations