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

    Neuronpedia

    INDEX
    Explanations

    Boxing/MMA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    patches
    -0.07
    open
    -0.07
    _THREAD
    -0.07
    kos
    -0.07
    ocard
    -0.06
    handles
    -0.06
     Firestore
    -0.06
    rollback
    -0.06
     automation
    -0.06
    Detection
    -0.06
    POSITIVE LOGITS
     급
    0.07
     Пом
    0.07
     останні
    0.06
     tells
    0.06
    .med
    0.06
    ILLS
    0.06
     も
    0.06
     бой
    0.06
     SOLD
    0.06
     Done
    0.06
    Act Density 0.012%

    No Known Activations