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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SKI
    -0.08
    حت
    -0.07
    LOG
    -0.07
    慢
    -0.07
    sequ
    -0.06
    PED
    -0.06
    Ein
    -0.06
     conformity
    -0.06
    掉
    -0.06
    INY
    -0.06
    POSITIVE LOGITS
    焕发
    0.07
    🅾
    0.07
    ༼
    0.07
    æ
    0.07
    新材料
    0.07
    utow
    0.07
    ₣
    0.07
    '];?></
    0.07
     Secure
    0.06
    />\
    0.06
    Act Density 0.159%

    No Known Activations