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

    Neuronpedia

    INDEX
    Explanations

    Formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tes
    -0.07
    istani
    -0.07
     alanında
    -0.06
    ينا
    -0.06
     Buster
    -0.06
     �
    -0.06
    ymm
    -0.06
     jejichž
    -0.06
    廳
    -0.06
    _dash
    -0.06
    POSITIVE LOGITS
    Richard
    0.07
     ث
    0.06
     println
    0.06
     remarkably
    0.06
     regulating
    0.06
     intermediate
    0.06
    	BYTE
    0.06
    Import
    0.06
     Kimberly
    0.06
     Including
    0.06
    Act Density 0.019%

    No Known Activations