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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    same
    -0.07
     Zimbabwe
    -0.07
     guesses
    -0.06
    均
    -0.06
    xl
    -0.06
    Spy
    -0.06
     Cheng
    -0.06
    achs
    -0.06
    FUN
    -0.06
    _theta
    -0.06
    POSITIVE LOGITS
    )))));↵
    0.07
    ']:
    0.07
     압
    0.07
     başv
    0.06
     Πανεπ
    0.06
     doğal
    0.06
     ]);
    0.06
    '])?
    0.06
    .localPosition
    0.06
     PUBLIC
    0.06
    Act Density 0.674%

    No Known Activations