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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     학교
    -0.07
     Swords
    -0.06
     parc
    -0.06
    +S
    -0.06
    byss
    -0.06
    VOID
    -0.06
     (),
    -0.06
    bows
    -0.05
    [parent
    -0.05
     bufferSize
    -0.05
    POSITIVE LOGITS
    577
    0.07
     securities
    0.07
    威
    0.07
    eful
    0.07
     '%$
    0.07
    _ed
    0.06
    _estimate
    0.06
    ケ
    0.06
    .free
    0.06
    notes
    0.06
    Act Density 0.250%

    No Known Activations