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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mart
    -0.07
    mas
    -0.07
    urrence
    -0.07
     Ου
    -0.06
     Engagement
    -0.06
     ES
    -0.06
    doors
    -0.06
     Gas
    -0.06
     TRI
    -0.06
    ﻴ
    -0.06
    POSITIVE LOGITS
    DateString
    0.06
     lamb
    0.06
    ¯
    0.06
    zk
    0.06
    ička
    0.06
    σκευ
    0.06
     Mexico
    0.06
    omid
    0.06
    _FIFO
    0.06
     undermine
    0.06
    Act Density 0.017%

    No Known Activations