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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERICA
    -0.07
    enet
    -0.07
    坚
    -0.07
     aided
    -0.06
     бу
    -0.06
     fed
    -0.06
     works
    -0.06
    =color
    -0.06
    .Named
    -0.06
    ]));↵↵
    -0.06
    POSITIVE LOGITS
    (us
    0.07
     dateTime
    0.06
    atak
    0.06
    (ic
    0.06
     webpack
    0.06
     bt
    0.06
    .number
    0.06
     Tile
    0.06
    .student
    0.06
    τος
    0.06
    Act Density 0.001%

    No Known Activations