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

    Neuronpedia

    INDEX
    Explanations

    website errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intellectually
    -0.07
     citations
    -0.07
     Frem
    -0.07
     bü
    -0.07
    ию
    -0.07
    lä
    -0.07
    lü
    -0.07
     Hü
    -0.07
     Klaus
    -0.06
    irs
    -0.06
    POSITIVE LOGITS
    疾病的
    0.06
    搬迁
    0.06
     pd
    0.06
    崩
    0.06
    ADER
    0.06
    /<?
    0.06
    링
    0.06
    unifu
    0.06
    QUENCY
    0.06
    胂
    0.06
    Act Density 0.001%

    No Known Activations