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

    Neuronpedia

    INDEX
    Explanations

    debates and arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     knockout
    -0.07
     align
    -0.07
     test
    -0.06
    наче
    -0.06
     ministers
    -0.06
     withstand
    -0.06
    ователь
    -0.06
     volunteering
    -0.06
    currentIndex
    -0.06
     suspense
    -0.06
    POSITIVE LOGITS
    Eb
    0.07
     सल
    0.06
     advoc
    0.06
     sluggish
    0.06
    quam
    0.06
    SACTION
    0.06
    _install
    0.06
     Rab
    0.06
     دریافت
    0.06
     qualities
    0.06
    Act Density 0.042%

    No Known Activations