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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungeon
    -0.07
    nown
    -0.07
     Pun
    -0.07
     nuova
    -0.07
    独一无
    -0.07
    貂
    -0.07
    诞
    -0.07
    �
    -0.07
    ан
    -0.07
    聪
    -0.06
    POSITIVE LOGITS
    Chapter
    0.07
    夜
    0.07
     reader
    0.07
     episodes
    0.07
     Selection
    0.07
     Citadel
    0.07
    Евро
    0.07
     Para
    0.07
     corrid
    0.07
    ='/
    0.06
    Act Density 0.030%

    No Known Activations