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

    Neuronpedia

    INDEX
    Explanations

    from in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    earer
    -0.07
    Visibility
    -0.07
     Trab
    -0.07
    zs
    -0.06
     Kas
    -0.06
     Christine
    -0.06
    tour
    -0.06
     cour
    -0.06
    atch
    -0.06
    Esta
    -0.06
    POSITIVE LOGITS
    uset
    0.07
    .fake
    0.06
    Dam
    0.06
     interpreting
    0.06
    _av
    0.06
     naken
    0.06
    _remote
    0.06
    }")↵
    0.06
    .every
    0.06
    ingroup
    0.06
    Act Density 0.048%

    No Known Activations