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

    Neuronpedia

    INDEX
    Explanations

    purpose when or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.20
    '
    0.19
    ().
    0.18
    ());
    0.18
    sufficient
    0.17
    );
    0.17
    info
    0.17
    0.17
    uerdo
    0.17
    ers
    0.17
    POSITIVE LOGITS
     when
    0.40
     cuando
    0.39
     для
    0.39
     quando
    0.38
     pentru
    0.38
     dalam
    0.37
     în
    0.36
     när
    0.36
    ในการ
    0.35
     ketika
    0.34
    Act Density 1.782%

    No Known Activations