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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asctime
    -0.07
    　　　　 　 　
    -0.07
    teenth
    -0.06
     Ark
    -0.06
    (fp
    -0.06
     noop
    -0.06
    려요
    -0.06
    dimension
    -0.06
    (padding
    -0.06
    ngrx
    -0.06
    POSITIVE LOGITS
     pause
    0.07
    -defense
    0.07
     repro
    0.06
    .(
    0.06
     pauses
    0.06
    delivery
    0.06
    .'/
    0.06
    ).(
    0.06
    Buttons
    0.06
     emphasis
    0.06
    Act Density 0.000%

    No Known Activations