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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vegan
    -0.07
    ليات
    -0.06
    opathy
    -0.06
     Sophia
    -0.06
    nave
    -0.06
    елю
    -0.06
     링
    -0.06
     развитие
    -0.06
    -powered
    -0.06
    神
    -0.06
    POSITIVE LOGITS
    shr
    0.07
    )viewDidLoad
    0.07
     esta
    0.06
    unned
    0.06
     dostal
    0.06
     entfer
    0.06
     �
    0.06
     regardless
    0.06
    ۱۹۸
    0.06
     bekannt
    0.06
    Act Density 0.029%

    No Known Activations