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

    Neuronpedia

    INDEX
    Explanations

    int

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     루
    -0.07
     coco
    -0.07
     ru
    -0.07
     pastoral
    -0.07
     kan
    -0.07
     NORMAL
    -0.07
     climate
    -0.06
     zarar
    -0.06
    *u
    -0.06
     pool
    -0.06
    POSITIVE LOGITS
    Script
    0.08
    DataService
    0.07
    -metadata
    0.06
    EXEC
    0.06
     Sidebar
    0.06
    Alpha
    0.06
    َت
    0.06
     سالم
    0.06
    .white
    0.06
    }"↵↵
    0.06
    Act Density 0.021%

    No Known Activations