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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     to
    -0.10
     To
    -0.09
    to
    -0.08
     TO
    -0.08
    To
    -0.07
    -to
    -0.07
    >To
    -0.07
     Parish
    -0.06
     from
    -0.06
     pend
    -0.06
    POSITIVE LOGITS
    ениями
    0.07
     Turing
    0.06
    owie
    0.06
    '][
    0.06
    odcast
    0.06
     Sonuç
    0.06
     wore
    0.06
    (fill
    0.06
     isIn
    0.06
    ึ่
    0.06
    Act Density 0.126%

    No Known Activations