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

    Neuronpedia

    INDEX
    Explanations

    time schedules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desired
    -0.08
     Conditions
    -0.07
     wealthy
    -0.07
    uples
    -0.06
    Defaults
    -0.06
     diagram
    -0.06
     halo
    -0.06
     pulling
    -0.06
    .+
    -0.06
    -handle
    -0.06
    POSITIVE LOGITS
     bombing
    0.07
    งก
    0.06
    PreparedStatement
    0.06
    styl
    0.06
     Kendrick
    0.06
    REW
    0.06
    丹
    0.06
     smr
    0.06
    realDonaldTrump
    0.06
    DEX
    0.06
    Act Density 0.014%

    No Known Activations