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

    Neuronpedia

    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τολ
    -0.07
    tiği
    -0.07
    )section
    -0.07
    ﻠ
    -0.07
    ×
    -0.07
    voie
    -0.07
    placement
    -0.07
     Sales
    -0.07
    ramento
    -0.07
    桥
    -0.06
    POSITIVE LOGITS
     man
    0.07
     bele
    0.07
     creates
    0.06
     did
    0.06
    _can
    0.06
     Kon
    0.06
     WITH
    0.06
     coined
    0.06
    ист
    0.06
     das
    0.06
    Act Density 0.000%

    No Known Activations