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

    Neuronpedia

    INDEX
    Explanations

    smallest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Эти
    -0.07
    _cookies
    -0.06
    church
    -0.06
     blasts
    -0.06
     submits
    -0.06
    έργ
    -0.06
     publishing
    -0.06
     ethanol
    -0.06
     attachments
    -0.06
    すべて
    -0.06
    POSITIVE LOGITS
    TO
    0.07
    Trip
    0.06
     Spec
    0.06
     Str
    0.06
    ‐-
    0.06
     Isis
    0.06
    官
    0.06
    #\
    0.06
     shuffle
    0.06
    .LinearLayoutManager
    0.06
    Act Density 0.000%

    No Known Activations