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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alfonso
    -0.08
     Genius
    -0.07
     genius
    -0.07
    SIGN
    -0.07
    優
    -0.07
     dibanding
    -0.07
     bitterness
    -0.07
     rumors
    -0.07
     Griffith
    -0.07
     Suzanne
    -0.07
    POSITIVE LOGITS
     enumeration
    0.13
     enumer
    0.12
     Enumeration
    0.11
    Enumeration
    0.11
    名单
    0.11
     Enumer
    0.10
     listar
    0.10
     Enumerable
    0.10
     перечис
    0.10
     Listing
    0.10
    Act Density 0.029%

    No Known Activations