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

    Neuronpedia

    INDEX
    Explanations

    HTML lists: ordered and unordered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പരാ
    0.40
     hücre
    0.38
    Pascal
    0.38
    araf
    0.37
    लेज
    0.37
    భవ
    0.37
    ពេ
    0.36
     பெண்
    0.36
    ರವ
    0.36
    brev
    0.36
    POSITIVE LOGITS
     unordered
    1.32
     ul
    1.30
     UL
    1.25
     ordered
    1.23
    unordered
    1.22
     Ordered
    1.20
    <ul>
    1.19
     Ul
    1.13
    Ordered
    1.13
    ordered
    1.11
    Act Density 0.030%

    No Known Activations