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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harley
    -0.06
    (mu
    -0.06
    児
    -0.06
    coder
    -0.06
    server
    -0.06
    -called
    -0.06
     useClass
    -0.06
     Theory
    -0.06
    (m
    -0.06
    享
    -0.06
    POSITIVE LOGITS
     impending
    0.07
    ecká
    0.07
    \xb
    0.06
    ряду
    0.06
    ΑΝ
    0.06
     ►
    0.06
    Obama
    0.06
    violent
    0.06
     hob
    0.06
     ох
    0.06
    Act Density 0.001%

    No Known Activations