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

    Neuronpedia

    INDEX
    Explanations

    Rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CSP
    -0.06
    168
    -0.06
    .repository
    -0.06
    _ts
    -0.06
     speculation
    -0.06
     sometimes
    -0.06
    然而
    -0.06
     fatally
    -0.06
    久
    -0.06
     left
    -0.06
    POSITIVE LOGITS
    contin
    0.08
     Dong
    0.07
     těla
    0.06
    ENTE
    0.06
     søger
    0.06
     anonym
    0.06
    Como
    0.06
     пн
    0.06
     sæ
    0.06
    ΑΝ
    0.06
    Act Density 0.059%

    No Known Activations