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

    Neuronpedia

    INDEX
    Explanations

    repository, developer, abilities, satellites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uq
    0.52
    us
    0.50
    olig
    0.48
    treat
    0.47
     بني
    0.46
    as
    0.46
     للك
    0.46
    ులు
    0.45
     بالك
    0.45
    iski
    0.44
    POSITIVE LOGITS
     penggunaan
    0.51
     aktif
    0.50
    時間
    0.48
     grasp
    0.48
     utilizzo
    0.47
    时间
    0.47
    <0xBD>
    0.46
    在
    0.45
     jäl
    0.45
    ચા
    0.45
    Act Density 0.002%

    No Known Activations