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

    Neuronpedia

    INDEX
    Explanations

    image generation prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     赵
    0.33
     Kxc
    0.32
     árvore
    0.32
     pribli
    0.31
    лд
    0.31
     imasmim
    0.31
    Კ
    0.31
     matplotlib
    0.30
    Љ
    0.30
    ക്ഷണ
    0.30
    POSITIVE LOGITS
    pr
    0.43
    sc
    0.37
    9
    0.35
    mer
    0.34
    ge
    0.34
    sh
    0.34
    pesar
    0.33
    mr
    0.33
    ibt
    0.33
    vol
    0.32
    Act Density 0.026%

    No Known Activations