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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asury
    -0.07
    坐
    -0.06
     sign
    -0.06
     Cow
    -0.06
     Manson
    -0.06
     Hong
    -0.06
     downtown
    -0.06
     Charter
    -0.06
     dial
    -0.06
     motorists
    -0.06
    POSITIVE LOGITS
     Ella
    0.07
    ΙΚΗ
    0.07
    	
↵
↵
    0.06
     ella
    0.06
     schön
    0.06
     remembered
    0.06
    >'.↵
    0.06
     граф
    0.06
    ليزية
    0.06
    áf
    0.06
    Act Density 0.003%

    No Known Activations