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

    Neuronpedia

    INDEX
    Explanations

    radio shows/journals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CENTER
    -0.07
    至关
    -0.07
    닌
    -0.06
     Tk
    -0.06
     onNext
    -0.06
    PN
    -0.06
    _JOIN
    -0.06
    言う
    -0.06
    IKE
    -0.06
     axiom
    -0.06
    POSITIVE LOGITS
    弨
    0.08
    🏝
    0.08
     supposed
    0.07
    德拉
    0.07
     afect
    0.07
    usaha
    0.07
    좀
    0.07
    .chapter
    0.07
     musica
    0.07
    Knowledge
    0.07
    Act Density 0.012%

    No Known Activations