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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĵģçīĮ形象
    -0.30
    [assembly
    -0.29
     modification
    -0.27
     modifying
    -0.27
    WER
    -0.26
    æĶ¹è¿Ľ
    -0.26
    æĹ¶ä»£ä¸ŃåĽ½
    -0.26
     modify
    -0.25
    ienes
    -0.25
    parate
    -0.25
    POSITIVE LOGITS
    ém
    0.28
     skÅĤad
    0.27
    usan
    0.26
    duk
    0.26
     Outlook
    0.25
     Politics
    0.25
    -disc
    0.25
    åħĭ
    0.24
    itung
    0.24
     Volt
    0.24
    Act Density 0.397%

    No Known Activations