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

    Neuronpedia

    INDEX
    Explanations

    cooking ingredients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	widget
    -0.08
     computes
    -0.06
    baum
    -0.06
    notations
    -0.06
     legislative
    -0.06
     Integrity
    -0.06
    ecture
    -0.06
    яс
    -0.06
     Que
    -0.06
    ости
    -0.06
    POSITIVE LOGITS
     Angie
    0.07
    �재
    0.07
    .timeScale
    0.06
     accordion
    0.06
    ้้
    0.06
     pravidel
    0.06
     위해서
    0.06
     Zoe
    0.06
     nightmare
    0.06
     hemos
    0.06
    Act Density 0.029%

    No Known Activations