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

    Neuronpedia

    INDEX
    Explanations

    code, text processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coal
    -0.07
    -hop
    -0.07
     nuis
    -0.07
    -Col
    -0.07
    щен
    -0.07
    ᶤ
    -0.07
    Zoom
    -0.07
    垡
    -0.07
     cục
    -0.06
    𬭁
    -0.06
    POSITIVE LOGITS
    📃
    0.08
     experience
    0.07
     EAR
    0.07
     presentation
    0.07
     -*-
    0.07
    ertura
    0.07
    ający
    0.06
    ('{{
    0.06
     HE
    0.06
     WHAT
    0.06
    Act Density 0.048%

    No Known Activations