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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bridges
    -0.07
     мне
    -0.06
    	use
    -0.06
    	foreach
    -0.06
     softer
    -0.06
     bridge
    -0.06
    、や
    -0.06
     对
    -0.06
     Lopez
    -0.06
    .TABLE
    -0.06
    POSITIVE LOGITS
     Accounting
    0.07
     wes
    0.07
    -decoration
    0.06
     Tasks
    0.06
    -notification
    0.06
     anatom
    0.06
     biography
    0.06
     nồi
    0.06
    '+↵
    0.06
    _STS
    0.06
    Act Density 0.002%

    No Known Activations