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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crushers
    -0.07
     sinus
    -0.06
    Zero
    -0.06
    .UseText
    -0.06
     pued
    -0.06
     +"
    -0.06
    .printf
    -0.06
     certifications
    -0.06
     Zot
    -0.06
    ιας
    -0.06
    POSITIVE LOGITS
     prio
    0.07
    _cleanup
    0.06
    인을
    0.06
    mq
    0.06
     blanket
    0.06
    ulfill
    0.06
     eksik
    0.06
    goal
    0.06
     blankets
    0.06
     Harrison
    0.06
    Act Density 0.002%

    No Known Activations