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

    Neuronpedia

    INDEX
    Explanations

    proof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curse
    -0.07
    ,L
    -0.07
    اختی
    -0.06
    立
    -0.06
     Division
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    istik
    -0.06
     Bol
    -0.06
    substring
    -0.06
    rač
    -0.06
    POSITIVE LOGITS
     вип
    0.07
     считается
    0.07
    :pk
    0.06
     Proof
    0.06
    υ
    0.06
     longtime
    0.06
     Vita
    0.06
     proof
    0.06
    \views
    0.06
     spreadsheet
    0.06
    Act Density 0.001%

    No Known Activations