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

    Neuronpedia

    INDEX
    Explanations

    Family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kendrick
    -0.09
     Novi
    -0.09
    DDR
    -0.08
    sharp
    -0.08
    @gmail
    -0.07
     কৰিছিল
    -0.07
    Lastname
    -0.07
    @test
    -0.07
     Bran
    -0.07
    ವಾಗಿ
    -0.07
    POSITIVE LOGITS
     excavation
    0.08
     έχουμε
    0.07
     RUB
    0.07
    ϋ
    0.07
     RIGHTS
    0.07
     Survival
    0.07
     popraw
    0.07
     corretamente
    0.07
    әм
    0.07
     صندوق
    0.07
    Act Density 0.000%

    No Known Activations