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

    Neuronpedia

    INDEX
    Explanations

    multiple, different, several instances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     несколь
    -0.08
     subjects
    -0.07
     sut
    -0.07
     Aer
    -0.07
    	e
    -0.07
     GK
    -0.07
    真人
    -0.07
     apro
    -0.07
     Nº
    -0.07
     اله
    -0.07
    POSITIVE LOGITS
    _vocab
    0.07
    amic
    0.07
    닪
    0.07
    Orig
    0.07
    מור
    0.07
    정보
    0.07
    orno
    0.07
    .gateway
    0.06
    �
    0.06
     Every
    0.06
    Act Density 0.148%

    No Known Activations