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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EDIATEK
    -0.07
    анг
    -0.07
    OX
    -0.07
    lední
    -0.07
    Flip
    -0.07
     ){
↵
    -0.07
     flaws
    -0.07
    **(
    -0.07
    رفت
    -0.06
    واز
    -0.06
    POSITIVE LOGITS
     possessions
    0.06
    932
    0.06
    ामन
    0.06
    -mouth
    0.06
    874
    0.06
     brace
    0.06
    alth
    0.06
    	token
    0.06
    -family
    0.06
     순간
    0.05
    Act Density 0.002%

    No Known Activations