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

    Neuronpedia

    INDEX
    Explanations

    elif dm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sideways
    0.42
    门
    0.42
    uí
    0.40
    alaman
    0.40
    ｸ
    0.38
    ﾍ
    0.37
    ｯ
    0.37
    curves
    0.36
    lusconi
    0.36
    굴
    0.36
    POSITIVE LOGITS
     kali
    0.38
     prv
    0.37
     Kali
    0.37
     Ums
    0.36
     Nove
    0.36
     Datas
    0.36
     siendo
    0.35
     нови
    0.35
     پلان
    0.34
    November
    0.34
    Act Density 0.003%

    No Known Activations