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

    Neuronpedia

    INDEX
    Explanations

    az

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Beta
    -0.07
    oters
    -0.07
    倍
    -0.07
    stories
    -0.07
     Rh
    -0.07
    ZF
    -0.07
     Drivers
    -0.07
     Miles
    -0.07
     En
    -0.07
    stoi
    -0.07
    POSITIVE LOGITS
    _tb
    0.06
    angling
    0.06
    леч
    0.06
     wasting
    0.06
     Malaysian
    0.06
    .jackson
    0.06
    addock
    0.06
    apture
    0.06
    ินทร
    0.06
     pending
    0.06
    Act Density 0.025%

    No Known Activations