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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chứa
    -0.07
     Tos
    -0.07
     demonstrating
    -0.07
    Guy
    -0.06
    omega
    -0.06
    district
    -0.06
     gồm
    -0.06
    Дата
    -0.06
    gree
    -0.06
    scheduled
    -0.06
    POSITIVE LOGITS
    (parent
    0.06
    衆
    0.06
    _IN
    0.06
    -in
    0.06
    _std
    0.06
     Packet
    0.06
    _pe
    0.06
    委
    0.05
    (QtCore
    0.05
     الد
    0.05
    Act Density 0.047%

    No Known Activations