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

    Neuronpedia

    INDEX
    Explanations

    database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FINAL
    -0.07
    ...'↵
    -0.07
     iPhones
    -0.06
    SER
    -0.06
    .Selection
    -0.06
    rxjs
    -0.06
    ']},↵
    -0.06
    	rec
    -0.06
    Kansas
    -0.06
     Scots
    -0.06
    POSITIVE LOGITS
     (()
    0.07
    山
    0.07
    .ToDecimal
    0.06
     nạn
    0.06
    (^
    0.06
    Mount
    0.06
    arty
    0.06
     AssertionError
    0.06
    bol
    0.06
    비
    0.06
    Act Density 0.012%

    No Known Activations