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

    Neuronpedia

    INDEX
    Explanations

    Figures and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KW
    -0.06
    TOTAL
    -0.06
     livre
    -0.06
     rua
    -0.06
     entity
    -0.06
     음악
    -0.06
    YES
    -0.06
    "user
    -0.06
    струмент
    -0.06
     astore
    -0.06
    POSITIVE LOGITS
    ;set
    0.07
    	UINT
    0.07
     derece
    0.07
     ReferentialAction
    0.06
     ปร
    0.06
    ẵng
    0.06
     caret
    0.06
     Mess
    0.06
    IllegalArgumentException
    0.06
     reopening
    0.06
    Act Density 0.019%

    No Known Activations