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

    Neuronpedia

    INDEX
    Explanations

    say 'arguments'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSE
    -0.07
    rema
    -0.07
     Obamacare
    -0.07
     mắt
    -0.07
    @extends
    -0.07
     הנא
    -0.07
     família
    -0.06
    다가
    -0.06
    orta
    -0.06
    ppe
    -0.06
    POSITIVE LOGITS
     Packet
    0.08
    EditingController
    0.07
    .unregister
    0.07
     Gerald
    0.07
     SCH
    0.07
    _DRIVER
    0.07
     OWN
    0.07
    导游
    0.07
    攻
    0.07
    sessions
    0.07
    Act Density 0.002%

    No Known Activations