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

    Neuronpedia

    INDEX
    Explanations

    philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulg
    -0.07
      
↵
    -0.07
     essays
    -0.07
     progresses
    -0.07
    ikut
    -0.06
    huge
    -0.06
    gger
    -0.06
    Republicans
    -0.06
    ють
    -0.06
    ativas
    -0.06
    POSITIVE LOGITS
    VisualStyle
    0.06
     банк
    0.06
    (Collections
    0.06
     місці
    0.06
    вание
    0.06
    мель
    0.06
    UMMY
    0.06
     naughty
    0.06
     indeb
    0.06
     BlackBerry
    0.06
    Act Density 0.022%

    No Known Activations