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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uid
    -0.07
     spre
    -0.07
     Exchange
    -0.06
    ETING
    -0.06
    \Modules
    -0.06
    eted
    -0.06
    -license
    -0.06
     Guy
    -0.06
    ":
    -0.06
     kort
    -0.06
    POSITIVE LOGITS
     wikipedia
    0.06
     dưới
    0.06
     ());↵
    0.06
    Previously
    0.06
    uffman
    0.06
    �
    0.06
    Jimmy
    0.06
    asonry
    0.06
    Decl
    0.06
     Instructions
    0.06
    Act Density 0.242%

    No Known Activations