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

    Neuronpedia

    INDEX
    Explanations

    attenuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .display
    -0.07
     вс
    -0.07
    	union
    -0.07
    揖
    -0.07
    -ion
    -0.06
    -high
    -0.06
     PATH
    -0.06
    筥
    -0.06
     Penn
    -0.06
     onclick
    -0.06
    POSITIVE LOGITS
    ぁ
    0.07
    0.07
    рит
    0.07
    ﺑ
    0.07
    0.07
    0.07
    摁
    0.07
     composing
    0.07
    0.07
    сен
    0.07
    Act Density 0.004%

    No Known Activations