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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いずれ
    -0.07
    �
    -0.07
     LOGIN
    -0.07
    芴
    -0.07
    烫
    -0.07
    �
    -0.06
     갖
    -0.06
    .nasa
    -0.06
     RPG
    -0.06
     cardio
    -0.06
    POSITIVE LOGITS
    逐渐
    0.08
     باستخدام
    0.07
    -ft
    0.07
    侵害
    0.07
    jść
    0.07
    🥇
    0.07
    .pipe
    0.06
    (ne
    0.06
    ")+
    0.06
    服務或
    0.06
    Act Density 0.054%

    No Known Activations