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

    Neuronpedia

    INDEX
    Explanations

    during

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parseFloat
    -0.07
     yarat
    -0.07
     coff
    -0.07
     net
    -0.07
    subtract
    -0.07
    _manual
    -0.06
    압
    -0.06
    ocument
    -0.06
    .Font
    -0.06
     aer
    -0.06
    POSITIVE LOGITS
     allowed
    0.07
     during
    0.06
    ↵
↵
↵
    0.06
     sealed
    0.06
     stays
    0.06
    Лю
    0.06
     Під
    0.06
    引き
    0.06
    apan
    0.06
    ;amp
    0.06
    Act Density 0.038%

    No Known Activations