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

    Neuronpedia

    INDEX
    Explanations

    tell tale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    퓰
    0.40
     сте
    0.40
     راحت
    0.39
    erode
    0.39
     denitr
    0.39
    گیرد
    0.39
    калә
    0.38
     tét
    0.38
     GLFW
    0.38
    кола
    0.37
    POSITIVE LOGITS
    uem
    0.36
    டர்
    0.35
     แ
    0.35
     আলম
    0.35
     far
    0.34
    zedł
    0.34
    í
    0.34
     aulas
    0.34
    ye
    0.33
    iem
    0.33
    Act Density 0.000%

    No Known Activations