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

    Neuronpedia

    INDEX
    Explanations

    random text passages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.80
    usitis
    -0.73
    Vidite
    -0.72
    AFFIRMED
    -0.72
    -0.72
    InitVars
    -0.68
    ronyms
    -0.67
     Hawking
    -0.67
    цездатний
    -0.67
     AssemblyCulture
    -0.65
    POSITIVE LOGITS
     تانيه
    0.77
     themſelves
    0.72
     Reſ
    0.65
     myſelf
    0.65
     Theſe
    0.65
     Diſ
    0.62
     forklar
    0.62
     ſtate
    0.62
     diſt
    0.60
     pleaſure
    0.59
    Act Density 0.036%

    No Known Activations