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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Governor
    -0.07
    masters
    -0.07
     Canberra
    -0.07
     governor
    -0.07
    COUNT
    -0.06
    того
    -0.06
    roid
    -0.06
     gusta
    -0.06
    レー
    -0.06
    íses
    -0.06
    POSITIVE LOGITS
     [[]
    0.07
    _FINE
    0.07
    (outfile
    0.06
     filename
    0.06
    .simpleButton
    0.06
     gui
    0.06
     sockfd
    0.06
     durability
    0.06
     fantast
    0.06
    (rule
    0.06
    Act Density 0.002%

    No Known Activations