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

    Neuronpedia

    INDEX
    Explanations

    movie plots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rival
    -0.07
     アイ
    -0.07
     alır
    -0.07
    setVisibility
    -0.06
     комплекс
    -0.06
     setters
    -0.06
     alo
    -0.06
     resistor
    -0.06
     üy
    -0.06
    .cg
    -0.06
    POSITIVE LOGITS
    ชอบ
    0.07
     SMART
    0.07
    Construction
    0.06
     inhabit
    0.06
     HelloWorld
    0.06
    úng
    0.06
    SuppressWarnings
    0.06
    �
    0.06
     Molly
    0.06
    Messenger
    0.06
    Act Density 0.005%

    No Known Activations