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

    Neuronpedia

    INDEX
    Explanations

    included

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responders
    -0.07
    ention
    -0.07
     עבר
    -0.07
     Advoc
    -0.07
    个多月
    -0.07
     Midnight
    -0.07
    recogn
    -0.07
    舣
    -0.07
     antibodies
    -0.07
     elevator
    -0.07
    POSITIVE LOGITS
     cleaner
    0.07
    getFile
    0.07
    &s
    0.06
     Mas
    0.06
     Glenn
    0.06
    inke
    0.06
    PLUGIN
    0.06
    chk
    0.06
    ("%
    0.06
    .ul
    0.06
    Act Density 0.024%

    No Known Activations