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

    Neuronpedia

    INDEX
    Explanations

    Denials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �合
    -0.06
    onium
    -0.06
     jumper
    -0.06
     ком
    -0.06
     basal
    -0.06
     median
    -0.05
    raki
    -0.05
     XPath
    -0.05
     Checkout
    -0.05
    065
    -0.05
    POSITIVE LOGITS
    (ray
    0.07
    センター
    0.07
    νηση
    0.07
     مسئله
    0.07
    luetooth
    0.07
     injustice
    0.07
     extradition
    0.06
     Frank
    0.06
    羽
    0.06
     nej
    0.06
    Act Density 0.091%

    No Known Activations