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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Persons
    -0.07
    џџџџ
    -0.06
     positivity
    -0.06
    ッ
    -0.06
     persons
    -0.06
     study
    -0.06
     crossorigin
    -0.06
     nob
    -0.06
     พฤษภาคม
    -0.06
     ();↵↵
    -0.06
    POSITIVE LOGITS
    クセ
    0.07
     Delaware
    0.06
    GIT
    0.06
    انون
    0.06
     진짜
    0.06
    사랑
    0.06
    83
    0.06
     ENG
    0.06
    اضی
    0.06
    Oracle
    0.05
    Act Density 0.001%

    No Known Activations