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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    วน
    -0.07
     частини
    -0.06
    ่อต
    -0.06
     Scatter
    -0.06
     Quy
    -0.06
    :C
    -0.06
    commands
    -0.06
     tôn
    -0.06
    �
    -0.06
     Sind
    -0.06
    POSITIVE LOGITS
    CTION
    0.07
    dock
    0.07
     advantages
    0.06
    erring
    0.06
     unfavorable
    0.06
     distraction
    0.06
     SECTION
    0.06
    러
    0.06
     TD
    0.06
    _traj
    0.06
    Act Density 0.000%

    No Known Activations