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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks/parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jiang
    -0.07
     Ley
    -0.07
    &o
    -0.06
    博士
    -0.06
     analyses
    -0.06
    _LT
    -0.06
    /DTD
    -0.06
     бути
    -0.06
    uli
    -0.06
     бед
    -0.06
    POSITIVE LOGITS
     revolves
    0.06
    elapsed
    0.06
    accur
    0.06
    (name
    0.06
    StackTrace
    0.06
    (package
    0.06
    ất
    0.06
     Omaha
    0.06
     DETAILS
    0.06
     relocate
    0.06
    Act Density 0.010%

    No Known Activations