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

    Neuronpedia

    INDEX
    Explanations

    asking for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endl
    2.42
    pictured
    2.38
    ا
    2.31
     appro
    2.30
    achron
    2.24
     poč
    2.22
     suspected
    2.18
    ać
    2.16
     polled
    2.15
     vos
    2.15
    POSITIVE LOGITS
     đỡ
    3.14
    াল
    2.48
    desk
    2.33
    닫
    2.20
    ان
    2.15
     ích
    2.15
    е
    2.01
    𝚍
    1.99
     ويكيپيديا
    1.95
    ن
    1.94
    Act Density 0.365%

    No Known Activations