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

    Neuronpedia

    INDEX
    Explanations

    as directed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ciò
    1.12
     conoscenza
    1.09
    1.06
     elettronica
    1.05
     tinham
    1.02
    িতেছি
    1.00
     preparazione
    1.00
     comuns
    0.99
     전류
    0.97
    conoc
    0.96
    POSITIVE LOGITS
    s
    1.23
    m
    1.23
    h
    1.08
    un
    1.06
    n
    1.05
    ע
    0.94
    ار
    0.89
    em
    0.86
    b
    0.86
     buddies
    0.85
    Act Density 0.000%

    No Known Activations