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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ULO
    -0.07
    awah
    -0.07
    の上
    -0.06
    nist
    -0.06
    igor
    -0.06
     Только
    -0.06
    ECTOR
    -0.06
     unreasonable
    -0.06
    PERT
    -0.06
     cryptocurrency
    -0.06
    POSITIVE LOGITS
    (Main
    0.08
     chambers
    0.07
     prioritize
    0.06
     ApplicationRecord
    0.06
    (uint
    0.06
     grade
    0.06
    (el
    0.06
    awn
    0.06
    』（
    0.06
     ai
    0.06
    Act Density 0.035%

    No Known Activations