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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Safety
    -0.07
     ===>
    -0.06
    Ymd
    -0.06
    ินเด
    -0.06
     Permit
    -0.06
     Roh
    -0.06
     RAW
    -0.06
     mega
    -0.06
     Incre
    -0.06
    "><!--
    -0.06
    POSITIVE LOGITS
    ชร
    0.06
     temiz
    0.06
     tres
    0.06
     Pyramid
    0.06
     vũ
    0.06
    ablytyped
    0.06
    lere
    0.06
     dul
    0.06
    tsy
    0.06
    icester
    0.06
    Act Density 0.000%

    No Known Activations