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

    Neuronpedia

    INDEX
    Explanations

    names meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.10
    irlas
    1.05
    あるいは
    1.04
     communaut
    1.01
    ].)
    1.00
    generally
    0.97
    Goss
    0.97
     respective
    0.96
    0.94
    cumulative
    0.93
    POSITIVE LOGITS
     قدم
    1.37
     怪
    1.37
     망
    1.30
    ೈನ್
    1.25
     太
    1.24
     멋
    1.18
     푸
    1.17
     ભગવાન
    1.15
     빛
    1.14
     невероят
    1.13
    Act Density 0.037%

    No Known Activations