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

    Neuronpedia

    INDEX
    Explanations

    wherein/whereby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iris
    -0.07
    raz
    -0.07
    itori
    -0.07
    Her
    -0.07
     gratis
    -0.07
     nar
    -0.07
    bris
    -0.07
    跑
    -0.06
     rumors
    -0.06
     les
    -0.06
    POSITIVE LOGITS
     whereby
    0.07
    ^-
    0.07
    _st
    0.06
    .setTo
    0.06
    wn
    0.06
    floor
    0.06
    092
    0.06
    _DF
    0.06
    }()↵
    0.06
    .DataContext
    0.06
    Act Density 0.008%

    No Known Activations