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

    Neuronpedia

    INDEX
    Explanations

    say ","

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     regenerated
    -0.08
    咻
    -0.07
    endez
    -0.07
    벵
    -0.07
    _VERTICAL
    -0.07
     CAD
    -0.07
    Premium
    -0.07
     synonymous
    -0.07
    侴
    -0.07
    cls
    -0.07
    POSITIVE LOGITS
    	 ↵
    0.08
    ");
↵
↵
    0.07
    kıl
    0.06
    서
    0.06
    	  ↵
    0.06
    大量的
    0.06
    히
    0.06
    ´t
    0.06
    也无法
    0.06
    .sequence
    0.06
    Act Density 0.021%

    No Known Activations