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

    Neuronpedia

    INDEX
    Explanations

    ame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apocalypse
    0.50
     Apocalypse
    0.48
    FixedWidth
    0.47
     made
    0.46
     حل
    0.46
     cryptography
    0.46
     DESIGN
    0.45
     गुप्त
    0.45
     sealed
    0.44
     बनाया
    0.44
    POSITIVE LOGITS
    u
    0.46
    and
    0.45
     Dos
    0.42
    excerpt
    0.42
    V
    0.42
    нув
    0.41
    oben
    0.40
     studie
    0.40
    L
    0.40
    偣
    0.40
    Act Density 0.000%

    No Known Activations