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

    Neuronpedia

    INDEX
    Explanations

    Psychology Today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.93
    dy
    0.82
    logout
    0.77
    ार्किक
    0.75
     impede
    0.73
    ب
    0.72
     pask
    0.70
    tions
    0.70
    liness
    0.69
    কারী
    0.68
    POSITIVE LOGITS
     لیګ
    1.01
    𝙘
    0.90
    啍
    0.87
     voh
    0.85
    е
    0.83
    +"|
    0.83
    в
    0.82
     résult
    0.82
     meie
    0.80
    Czas
    0.80
    Act Density 0.022%

    No Known Activations