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

    Neuronpedia

    INDEX
    Explanations

    homes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snowy
    -0.07
     AMA
    -0.07
     ultimately
    -0.07
    σω
    -0.06
     seront
    -0.06
     Leah
    -0.06
    .moveTo
    -0.06
    wel
    -0.06
     Pret
    -0.06
     مکان
    -0.06
    POSITIVE LOGITS
    (uri
    0.07
    Jimmy
    0.07
     cảnh
    0.07
     kapit
    0.06
     perc
    0.06
    Undefined
    0.06
     uphold
    0.06
     Jimmy
    0.06
     exercitation
    0.06
    !"
    0.06
    Act Density 0.015%

    No Known Activations