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

    Neuronpedia

    INDEX
    Explanations

    display counts/ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     furnace
    -0.08
    迎接
    -0.07
    矾
    -0.07
    oblin
    -0.07
    FormControl
    -0.07
    Elite
    -0.07
     soph
    -0.07
    elt
    -0.06
     practically
    -0.06
    Adult
    -0.06
    POSITIVE LOGITS
     כתב
    0.07
     הציב
    0.07
     Supports
    0.07
    players
    0.07
     precisa
    0.06
    CBD
    0.06
     وضع
    0.06
    
    0.06
    질
    0.06
    (sentence
    0.06
    Act Density 0.005%

    No Known Activations