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
    _base
    -0.07
    フォ
    -0.06
    마사지
    -0.06
     Phát
    -0.06
     Alexandria
    -0.06
     discussing
    -0.06
     mav
    -0.06
    .Rest
    -0.06
     Các
    -0.06
     Liga
    -0.06
    POSITIVE LOGITS
    ANNOT
    0.07
     голову
    0.07
    都不
    0.07
    OAD
    0.06
    uggested
    0.06
     revised
    0.06
    edges
    0.06
    .sy
    0.06
    ainted
    0.06
    OMEM
    0.06
    Act Density 0.841%

    No Known Activations