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

    Neuronpedia

    INDEX
    Explanations

    wide range of applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.36
    ק
    1.35
    </h2>
    1.26
    rt
    1.13
    </b>
    1.12
     as
    1.11
    л
    1.11
    </th>
    1.10
     on
    1.10
    that
    1.09
    POSITIVE LOGITS
    (
    1.45
    {
    1.20
    ες
    1.05
    不愿意
    1.03
    ἲ
    1.02
    টি
    1.02
     broadened
    1.02
     inequ
    1.01
     promulg
    1.00
    かつ
    0.99
    Act Density 0.166%

    No Known Activations