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

    Neuronpedia

    INDEX
    Explanations

    document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     care
    -0.42
    Care
    -0.41
     dor
    -0.37
    atov
    -0.37
    CEN
    -0.36
    tid
    -0.36
     es
    -0.35
     remé
    -0.35
     therap
    -0.35
    isting
    -0.35
    POSITIVE LOGITS
     يتيمه
    0.80
     متعلقه
    0.75
    Autoritní
    0.75
     Majefty
    0.73
     >=",
    0.73
     Efq
    0.71
    الإنجليزية
    0.70
    ">//
    0.67
    Билгалдахарш
    0.66
     CreateTagHelper
    0.66
    Act Density 0.000%

    No Known Activations