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

    Neuronpedia

    INDEX
    Explanations

    scripted dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    boldsymbol
    0.40
     रिस
    0.39
    米
    0.39
     dort
    0.38
    රා
    0.37
    jour
    0.37
    tena
    0.36
     Ni
    0.36
     લોકો
    0.36
     bericht
    0.35
    POSITIVE LOGITS
     длин
    0.44
     высоких
    0.41
    apanam
    0.40
    Џ
    0.39
    حدیث
    0.39
     লম্বা
    0.39
    ἃ
    0.39
     लंबा
    0.38
    谷歌
    0.38
    вій
    0.38
    Act Density 0.000%

    No Known Activations