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

    Neuronpedia

    INDEX
    Explanations

    results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gems
    -0.08
    _blog
    -0.07
    .my
    -0.07
    .arch
    -0.07
    .WHITE
    -0.07
    My
    -0.07
     لف
    -0.07
    loquent
    -0.07
    -my
    -0.07
    (forms
    -0.07
    POSITIVE LOGITS
     трех
    0.06
     οικο
    0.06
    terior
    0.06
     cevap
    0.06
     TZ
    0.06
     것으로
    0.06
    uppe
    0.06
     newText
    0.06
    /modal
    0.06
     subtitle
    0.06
    Act Density 0.017%

    No Known Activations