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

    Neuronpedia

    INDEX
    Explanations

    code and technical continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "|
    0.45
     avsl
    0.39
    ไม่ได้
    0.38
     Steve
    0.38
    ोटे
    0.36
     "-",
    0.36
     posta
    0.36
     Beyond
    0.35
     steve
    0.35
     Much
    0.35
    POSITIVE LOGITS
    where
    0.41
     trabalh
    0.40
    idding
    0.40
    ricanes
    0.39
    ⁾
    0.39
    ude
    0.38
    ulsions
    0.38
    WORKDIR
    0.38
    use
    0.37
    ধ্যার
    0.37
    Act Density 0.067%

    No Known Activations