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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .);↵
    -0.08
     Belt
    -0.07
     trophy
    -0.07
    icolor
    -0.06
    /nav
    -0.06
     encountered
    -0.06
    definition
    -0.06
    erro
    -0.06
     Reed
    -0.06
    descripcion
    -0.06
    POSITIVE LOGITS
     Leaving
    0.07
    (kwargs
    0.07
     someone
    0.07
    ."<
    0.07
     وقد
    0.07
    <K
    0.06
     numerous
    0.06
    _SIGNAL
    0.06
    ]</
    0.06
    hoc
    0.06
    Act Density 0.001%

    No Known Activations