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

    Neuronpedia

    INDEX
    Explanations

    VPN services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    te
    1.86
    ft
    1.86
    ième
    1.84
     ràng
    1.74
    ν
    1.63
    se
    1.61
    ru
    1.59
    써
    1.58
     Bản
    1.48
    lo
    1.47
    POSITIVE LOGITS
    с
    1.89
    на
    1.84
    ின்
    1.81
    ﻭ
    1.71
    ﺭ
    1.70
    ﻝ
    1.70
    ায়
    1.68
    س
    1.68
    ючи
    1.67
    fueled
    1.67
    Act Density 0.000%

    No Known Activations