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

    Neuronpedia

    INDEX
    Explanations

    Gates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McKay
    -0.07
     Completely
    -0.06
    不可
    -0.06
    ังหว
    -0.06
     Honour
    -0.06
     �
    -0.06
    чай
    -0.06
    丁目
    -0.06
    .SK
    -0.06
     ideals
    -0.06
    POSITIVE LOGITS
     Gates
    0.09
     gates
    0.07
    Eng
    0.07
     destruct
    0.07
     travelled
    0.07
     leds
    0.07
     síd
    0.06
     executes
    0.06
    嘴
    0.06
    ็กชาย
    0.06
    Act Density 0.001%

    No Known Activations