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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilor
    -0.07
    油
    -0.06
     chall
    -0.06
     "(
    -0.06
    .iOS
    -0.06
    λω
    -0.06
    xDE
    -0.06
     범
    -0.06
    âb
    -0.06
     Janeiro
    -0.06
    POSITIVE LOGITS
    orraine
    0.07
    Ka
    0.07
     автомоб
    0.06
    scratch
    0.06
    Displayed
    0.06
    fu
    0.06
    .fromRGBO
    0.06
     For
    0.06
    *******
    0.06
    пис
    0.06
    Act Density 0.072%

    No Known Activations