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

    Neuronpedia

    INDEX
    Explanations

    Japanese, Korean, French, Spanish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İK
    0.39
    𝐘
    0.35
    İN
    0.35
     ساين
    0.35
    㸸
    0.35
    𝐓
    0.34
    唓
    0.34
    ⤥
    0.34
    SCHRAMM
    0.34
    𝗗
    0.34
    POSITIVE LOGITS
     k
    0.40
    h
    0.38
     h
    0.37
    iy
    0.36
     y
    0.35
    ma
    0.35
     na
    0.35
    ka
    0.35
     t
    0.34
     ku
    0.34
    Act Density 0.155%

    No Known Activations