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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    496
    -0.07
    驱
    -0.07
     Amp
    -0.07
    Honestly
    -0.06
     inhibition
    -0.06
    -lite
    -0.06
     onTouch
    -0.06
     Marble
    -0.06
    lamp
    -0.06
     produ
    -0.06
    POSITIVE LOGITS
    VES
    0.07
    remainder
    0.07
     příliš
    0.06
    brıs
    0.06
    children
    0.06
    ?$
    0.06
     Boca
    0.06
     σει
    0.06
    Plain
    0.06
    عان
    0.06
    Act Density 0.000%

    No Known Activations