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

    Neuronpedia

    INDEX
    Explanations

    geometry configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    能
    2.37
    ून
    2.15
     здоров
    2.07
    াধিক
    1.96
    п
    1.95
    দের
    1.94
    ़
    1.85
     dons
    1.83
     devo
    1.80
    ри
    1.77
    POSITIVE LOGITS
    cích
    2.93
    cısı
    2.93
    𝒋
    2.77
    cence
    2.75
    c
    2.71
     comenz
    2.69
    gom
    2.69
    yyyyyyyy
    2.68
    guez
    2.66
    нде
    2.66
    Act Density 0.002%

    No Known Activations