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

    Neuronpedia

    INDEX
    Explanations

    comes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     решение
    -0.07
     objedn
    -0.06
    級
    -0.06
    -Origin
    -0.06
     absol
    -0.06
     dyst
    -0.06
     Killed
    -0.06
    ntag
    -0.06
     favored
    -0.06
     gdb
    -0.06
    POSITIVE LOGITS
     comes
    0.07
     UIBarButtonItem
    0.07
    戶
    0.07
    (rename
    0.06
     flirting
    0.06
     sliders
    0.06
    .instant
    0.06
     wont
    0.06
    存档
    0.06
    high
    0.06
    Act Density 0.004%

    No Known Activations