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

    Neuronpedia

    INDEX
    Explanations

    anything/nothing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Emergency
    -0.07
    _quantity
    -0.07
     doing
    -0.06
    _attach
    -0.06
    private
    -0.06
    Given
    -0.06
    роме
    -0.06
    _Group
    -0.06
     First
    -0.06
     snakes
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.07
    resden
    0.07
     Kế
    0.07
    ونی
    0.06
    <Student
    0.06
    .vstack
    0.06
    ционного
    0.06
     Initi
    0.06
     defaultManager
    0.06
     maté
    0.06
    Act Density 0.017%

    No Known Activations