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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recv
    -0.07
    ("--
    -0.07
    veh
    -0.06
    EEE
    -0.06
     DatePicker
    -0.06
    ǎ
    -0.06
    _CRITICAL
    -0.06
     نگهد
    -0.06
    ？」
    -0.06
    >-->↵
    -0.06
    POSITIVE LOGITS
    ان
    0.08
    abb
    0.06
    it
    0.06
    _PLAN
    0.06
    лен
    0.06
     čtvrt
    0.06
     sandbox
    0.06
     columnIndex
    0.06
    َان
    0.06
     nomin
    0.06
    Act Density 0.061%

    No Known Activations