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

    Neuronpedia

    INDEX
    Explanations

    digital camera images

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    הבנה
    -0.08
    Operators
    -0.08
     Station
    -0.07
     shrink
    -0.07
     tofu
    -0.07
    apus
    -0.07
     deposits
    -0.07
     objetos
    -0.07
     hardest
    -0.07
     Manus
    -0.07
    POSITIVE LOGITS
    跌幅
    0.08
    DAL
    0.07
    .Padding
    0.07
     getDescription
    0.07
    卞
    0.07
     feed
    0.06
     cha
    0.06
    童装
    0.06
     Zach
    0.06
    .sql
    0.06
    Act Density 0.052%

    No Known Activations