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

    Neuronpedia

    INDEX
    Explanations

    Thanking / gratitude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Composite
    -0.08
     років
    -0.07
    Sounds
    -0.07
    fp
    -0.07
     exposure
    -0.06
     Toxic
    -0.06
    _Var
    -0.06
     flexible
    -0.06
     economic
    -0.06
     attendees
    -0.06
    POSITIVE LOGITS
    패
    0.07
    (PropertyName
    0.06
    InputChange
    0.06
    paced
    0.06
    ZE
    0.06
    (task
    0.06
    .GetEnumerator
    0.06
    .override
    0.06
    <D
    0.06
    ENE
    0.06
    Act Density 0.043%

    No Known Activations