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

    Neuronpedia

    INDEX
    Explanations

    strong emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    інг
    -0.08
    uckle
    -0.08
     scratch
    -0.07
     gang
    -0.07
     palms
    -0.07
     celebrated
    -0.07
     نش
    -0.07
     guided
    -0.07
    achts
    -0.07
    ाव
    -0.06
    POSITIVE LOGITS
    {l
    0.07
     双线
    0.06
     suger
    0.06
     дает
    0.06
    	bar
    0.05
     ><
    0.05
    .ts
    0.05
     следует
    0.05
    classes
    0.05
     produk
    0.05
    Act Density 0.215%

    No Known Activations