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

    Neuronpedia

    INDEX
    Explanations

    UTF-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avacak
    0.42
     kttt
    0.39
    "،
    0.37
     nodeList
    0.36
    າມາດ
    0.35
    မ့်
    0.35
     cristianos
    0.35
    紥
    0.34
     hồng
    0.34
     humains
    0.34
    POSITIVE LOGITS
    using
    0.40
    special
    0.36
    subject
    0.34
    void
    0.33
    tin
    0.33
    io
    0.33
    Real
    0.32
    bio
    0.32
    titan
    0.32
    rel
    0.32
    Act Density 0.000%

    No Known Activations