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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warehouses
    -0.07
     wah
    -0.07
    -0.07
    ?>">
↵
    -0.06
    hil
    -0.06
    rog
    -0.06
     played
    -0.06
     ledge
    -0.06
    rapy
    -0.06
    لس
    -0.06
    POSITIVE LOGITS
    717
    0.07
    ilyn
    0.06
    ustomed
    0.06
     att
    0.06
     Observable
    0.06
    ORIZ
    0.06
     거래
    0.06
    彡
    0.06
    [ix
    0.06
    _bs
    0.06
    Act Density 0.000%

    No Known Activations