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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getAll
    -0.07
    ili
    -0.06
     miscellaneous
    -0.06
    ськими
    -0.06
    mousedown
    -0.06
    běhu
    -0.06
    eckého
    -0.06
    jsp
    -0.06
    Connector
    -0.06
     newValue
    -0.06
    POSITIVE LOGITS
     변경
    0.07
     punched
    0.07
     mask
    0.07
    lu
    0.07
    paced
    0.06
    嗎
    0.06
    Thank
    0.06
     racked
    0.06
     lied
    0.06
    games
    0.06
    Act Density 0.027%

    No Known Activations