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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    english
    -0.91
    WriteLiteral
    -0.81
     autorytatywna
    -0.81
     AssemblyCulture
    -0.72
     injury
    -0.71
    MemoryWarning
    -0.71
     &___
    -0.68
     grève
    -0.68
    abestanden
    -0.68
     vœux
    -0.68
    POSITIVE LOGITS
     Ory
    0.48
    sup
    0.47
    <>
    0.47
     Cow
    0.46
     coyote
    0.46
    ees
    0.45
     Cre
    0.45
     Tier
    0.45
    ">:
    0.45
     Sor
    0.44
    Act Density 0.068%

    No Known Activations