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

    Neuronpedia

    INDEX
    Explanations

    Lisa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ny
    -0.07
     Strength
    -0.07
    *X
    -0.06
    	template
    -0.06
    *v
    -0.06
     Cu
    -0.06
    Played
    -0.06
    719
    -0.06
    Av
    -0.06
    ～
    -0.06
    POSITIVE LOGITS
     Lisa
    0.07
    osloven
    0.07
    適
    0.07
     hoses
    0.06
     useStyles
    0.06
     نتیجه
    0.06
     blanc
    0.06
    $wp
    0.06
    ucchini
    0.06
     tuna
    0.06
    Act Density 0.001%

    No Known Activations