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

    Neuronpedia

    INDEX
    Explanations

    data diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vara
    0.86
    ्यारह
    0.82
     pageSize
    0.79
    ighter
    0.79
    𝑒
    0.78
    aroos
    0.78
    ‫
    0.78
     Ill
    0.77
    ves
    0.77
    ishly
    0.76
    POSITIVE LOGITS
    e
    1.01
    ]");
    0.85
    snp
    0.84
    ean
    0.81
    €¦
    0.81
    <unused1160>
    0.81
    USSR
    0.81
    omenclature
    0.80
    იმ
    0.79
    KeyboardMarkup
    0.79
    Act Density 0.016%

    No Known Activations