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

    Neuronpedia

    INDEX
    Explanations

    moon, month, twice, teaching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐝
    1.35
     conver
    1.35
    ಯಲ್ಲಿ
    1.32
     Gens
    1.29
    Parad
    1.28
    Phenyl
    1.27
     permut
    1.26
    spr
    1.25
     Eats
    1.24
    Generalized
    1.23
    POSITIVE LOGITS
    かった
    1.20
    ště
    1.19
    ši
    1.13
    kep
    1.12
    ोत्तर
    1.09
    asjonen
    1.07
     protes
    1.06
     bull
    1.04
    álně
    1.03
    őt
    1.03
    Act Density 0.000%

    No Known Activations