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

    Neuronpedia

    INDEX
    Explanations

    tiramisu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ות
    1.35
    Ts
    1.19
    larni
    1.10
    ње
    1.09
    u
    1.09
    Ů
    1.06
    utage
    1.03
    UR
    1.02
    ństw
    1.01
     ідэ
    1.00
    POSITIVE LOGITS
     Chronic
    1.13
    した
    1.10
    FBSDKGraph
    1.10
     PASS
    1.08
    ما
    1.05
    دو
    1.05
     должность
    1.04
    但也
    1.04
    汩
    1.04
    したら
    1.02
    Act Density 0.001%

    No Known Activations