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

    Neuronpedia

    INDEX
    Explanations

    I/O and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atuur
    0.82
    ature
    0.72
    aturas
    0.69
     فال
    0.69
    ையான
    0.66
    ation
    0.65
    емые
    0.64
    atur
    0.64
    ํา
    0.62
    ant
    0.62
    POSITIVE LOGITS
     IDC
    0.84
    consulté
    0.84
     encompass
    0.83
     environmental
    0.81
     dbc
    0.78
     containing
    0.77
     bencana
    0.77
     پیس
    0.76
     Vr
    0.76
    IDC
    0.76
    Act Density 0.088%

    No Known Activations