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

    Neuronpedia

    INDEX
    Explanations

    deaths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     million
    -1.10
     loss
    -1.10
     millions
    -1.04
    millions
    -1.01
     dying
    -0.99
     deaths
    -0.96
     miljoner
    -0.89
     millón
    -0.88
     Millionen
    -0.88
     Millions
    -0.86
    POSITIVE LOGITS
     of
    0.55
     kok
    0.51
    (!
    0.50
    -
    0.50
    (
    0.49
    ,
    0.48
    light
    0.44
    .
    0.43
    +
    0.43
     kel
    0.42
    Act Density 0.044%

    No Known Activations