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

    Neuronpedia

    INDEX
    Explanations

    Bag

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     test
    -0.07
     ricerca
    -0.07
     Phillips
    -0.07
     Test
    -0.07
    刻
    -0.06
    mann
    -0.06
     Mater
    -0.06
    .Native
    -0.06
     yacht
    -0.06
    顿
    -0.06
    POSITIVE LOGITS
    ですね
    0.07
     bulun
    0.06
     başvur
    0.06
    Jul
    0.06
     生命周期
    0.06
    060
    0.06
    _logits
    0.06
    	un
    0.06
    わたし
    0.06
    abcdefghijklmnop
    0.06
    Act Density 0.003%

    No Known Activations