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

    Neuronpedia

    INDEX
    Explanations

    brackets, quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imageSize
    -0.06
     nóng
    -0.06
    ula
    -0.06
     executing
    -0.06
    .cz
    -0.06
     Zhang
    -0.06
     TZ
    -0.06
    атар
    -0.06
    fq
    -0.06
    ело
    -0.06
    POSITIVE LOGITS
    /demo
    0.07
     foundational
    0.06
    울
    0.06
     {"
    0.06
    …↵↵
    0.06
    emiah
    0.06
    Conn
    0.06
     στρα
    0.06
     deux
    0.06
     微
    0.06
    Act Density 0.155%

    No Known Activations