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

    Neuronpedia

    INDEX
    Explanations

    cognitive biases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Altern
    -0.07
    ½
    -0.07
    Hello
    -0.07
    Around
    -0.07
    (io
    -0.06
    software
    -0.06
     Introduction
    -0.06
     anale
    -0.06
     swapped
    -0.06
     God
    -0.06
    POSITIVE LOGITS
    _policy
    0.07
     RequestMethod
    0.06
     жит
    0.06
    ::_('
    0.06
    πού
    0.06
     chăm
    0.06
    .itemId
    0.06
    mp
    0.06
    .Plugin
    0.06
     Vegan
    0.06
    Act Density 0.089%

    No Known Activations