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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    елів
    -0.08
    Row
    -0.07
     komunik
    -0.07
    -rock
    -0.07
     людина
    -0.06
     عزیز
    -0.06
     butterflies
    -0.06
    	sb
    -0.06
     collaborative
    -0.06
     ziy
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    .play
    0.06
     feminism
    0.06
    ANCH
    0.06
     untrue
    0.06
    .getOwnProperty
    0.06
     Neither
    0.06
    ‌تواند
    0.06
    }/${
    0.06
    .socket
    0.06
    Act Density 0.017%

    No Known Activations