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

    Neuronpedia

    INDEX
    Explanations

    Study scores and indexes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _characters
    -0.07
     Rud
    -0.07
     Luc
    -0.06
    �
    -0.06
     chap
    -0.06
    _vars
    -0.06
    (do
    -0.06
     Franco
    -0.06
    Bon
    -0.06
    Suc
    -0.06
    POSITIVE LOGITS
    �璃
    0.07
     आय
    0.06
    oğ
    0.06
    KANJI
    0.06
     공지
    0.06
     Tipo
    0.06
    POOL
    0.06
    티
    0.06
     ESPN
    0.06
    -status
    0.06
    Act Density 0.036%

    No Known Activations