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

    Neuronpedia

    INDEX
    Explanations

    list items or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ني
    0.50
    IN
    0.47
    ON
    0.46
    ار
    0.44
    I
    0.43
    ER
    0.43
    ρηση
    0.42
    Inode
    0.42
     虽然
    0.42
    ELL
    0.41
    POSITIVE LOGITS
    a
    0.63
    ת
    0.63
    us
    0.57
    d
    0.52
    the
    0.50
    ↵
    0.49
    m
    0.48
    es
    0.46
    and
    0.45
    고
    0.45
    Act Density 2.126%

    No Known Activations