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

    Neuronpedia

    INDEX
    Explanations

    test results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bersome
    -0.07
    ší
    -0.07
     billionaires
    -0.06
    通信
    -0.06
    entario
    -0.06
     ----------↵
    -0.06
    htm
    -0.06
     RECORD
    -0.06
    _EXPI
    -0.06
     therein
    -0.06
    POSITIVE LOGITS
     탈
    0.07
     дев
    0.06
     cling
    0.06
     Judicial
    0.06
     tanım
    0.06
    epam
    0.06
     clientele
    0.06
    ůst
    0.06
    .ecore
    0.06
     oku
    0.06
    Act Density 0.027%

    No Known Activations