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

    Neuronpedia

    INDEX
    Explanations

    rules, bans, regulations

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases describing government-imposed restrictions or bans on an app for official devices.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exists
    -0.06
    >Total
    -0.06
    Super
    -0.06
    "W
    -0.06
    ArrayOf
    -0.06
     brief
    -0.05
     网
    -0.05
    ETYPE
    -0.05
    .radians
    -0.05
     Fly
    -0.05
    POSITIVE LOGITS
     стак
    0.07
     reservation
    0.07
     prolifer
    0.07
    owers
    0.07
    .Butter
    0.07
    amento
    0.06
    uckland
    0.06
    direct
    0.06
    _PE
    0.06
     Russell
    0.06
    Act Density 0.006%

    No Known Activations