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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <len
    -0.07
    堡垒
    -0.07
    ORIZONTAL
    -0.07
    =#
    -0.07
    .glide
    -0.07
     Issue
    -0.07
     companion
    -0.06
    �
    -0.06
    ChangeEvent
    -0.06
     sis
    -0.06
    POSITIVE LOGITS
     نقاط
    0.08
    ผม
    0.07
    いない
    0.07
    我觉得
    0.07
    reib
    0.07
     Peel
    0.07
     HK
    0.07
     Gloves
    0.06
     المنتخب
    0.06
     jung
    0.06
    Act Density 0.200%

    No Known Activations