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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _widget
    -0.07
    	Description
    -0.07
    Chunks
    -0.07
     Комп
    -0.06
    unami
    -0.06
    _correction
    -0.06
    .assertFalse
    -0.06
     Unidos
    -0.06
    (Index
    -0.06
    /Login
    -0.06
    POSITIVE LOGITS
     troublesome
    0.07
     controversies
    0.07
     Comfort
    0.06
     cualquier
    0.06
    ^\
    0.06
     genuine
    0.06
    _proof
    0.06
    ların
    0.06
    Immediate
    0.06
    schema
    0.06
    Act Density 0.002%

    No Known Activations