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

    Neuronpedia

    INDEX
    Explanations

    latex document classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     தோல்
    0.40
     rojos
    0.40
     आवड
    0.40
     احترام
    0.40
    JSONException
    0.39
    藿
    0.39
     creazione
    0.39
     distribuzione
    0.38
     பெயரை
    0.38
     toit
    0.38
    POSITIVE LOGITS
    вшим
    0.41
    𝙋
    0.39
    𝘀
    0.39
     Baylor
    0.38
     $:=$
    0.38
    𝙥
    0.37
     Superior
    0.37
    btnUn
    0.37
     bishop
    0.36
     yp
    0.36
    Act Density 0.001%

    No Known Activations