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

    Neuronpedia

    INDEX
    Explanations

    Positive descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')==
    -0.07
    bsub
    -0.07
     gameObject
    -0.06
    ’elle
    -0.06
    ﱵ
    -0.06
    ☴
    -0.06
    ᄄ
    -0.06
    ㈲
    -0.06
     department
    -0.06
    万多
    -0.06
    POSITIVE LOGITS
     макс
    0.08
     Reminder
    0.08
    .Invalid
    0.08
    Order
    0.07
    舍
    0.07
     Photography
    0.07
    ursions
    0.07
    Sorry
    0.07
    ["
    0.07
    _snapshot
    0.07
    Act Density 0.215%

    No Known Activations