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

    Neuronpedia

    INDEX
    Explanations

    Article/post snippets with dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åºł
    -0.25
    èĨĬ
    -0.25
    çĺ°
    -0.24
     окол
    -0.24
     programmed
    -0.24
    acob
    -0.24
    éķ¿è¾Ī
    -0.24
     chimney
    -0.23
    logic
    -0.23
     Neighborhood
    -0.23
    POSITIVE LOGITS
     Fargo
    0.28
     fullPath
    0.28
     hn
    0.27
     remaining
    0.27
    anz
    0.27
    åĮħåĮħ
    0.26
    æŶéĹ´ä¸º
    0.26
    remaining
    0.26
     hl
    0.25
    isce
    0.25
    Act Density 0.008%

    No Known Activations