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

    Neuronpedia

    INDEX
    Explanations

    Subtracting in equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     од
    -0.07
     ogni
    -0.07
     stesso
    -0.07
    ເ
    -0.07
    Roger
    -0.07
     operators
    -0.07
    Grand
    -0.07
    ﭘ
    -0.06
    ראית
    -0.06
     prz
    -0.06
    POSITIVE LOGITS
    	WebElement
    0.07
    _EXECUTE
    0.07
     press
    0.07
     lname
    0.07
     клуб
    0.06
    SSION
    0.06
    |
    0.06
    ied
    0.06
    炣
    0.06
    elp
    0.06
    Act Density 0.004%

    No Known Activations