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

    Neuronpedia

    INDEX
    Explanations

    injury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    港澳
    -0.29
    侧éĿ¢
    -0.27
    pol
    -0.26
    顺
    -0.26
     SIN
    -0.26
    æĺ¥é£İ
    -0.25
    Lifetime
    -0.25
    Living
    -0.25
    erry
    -0.25
    èģĶ
    -0.25
    POSITIVE LOGITS
    ...');↵
    0.29
    æĬķ票
    0.27
    exterity
    0.27
     THREAD
    0.27
    elon
    0.26
    ...')↵
    0.26
    ector
    0.26
    ...");č↵
    0.25
     pitchers
    0.25
    çĽ²çĽ®
    0.24
    Act Density 1.227%

    No Known Activations