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

    Neuronpedia

    INDEX
    Explanations

    terms commonly found in scientific studies

    oai_token-act-pair · gemini-2.0-flash

    research findings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.65
     незавершена
    -0.59
    &__
    -0.58
     تكبرها
    -0.57
    istible
    -0.56
    بوابة
    -0.54
    énario
    -0.54
    entist
    -0.54
    PerformLayout
    -0.53
     OFDb
    -0.51
    POSITIVE LOGITS
    DotNetBar
    0.68
     may
    0.62
     MainAxisSize
    0.59
     nakalista
    0.53
     NgModule
    0.51
     might
    0.51
    may
    0.50
     Possibly
    0.50
    openzeppelin
    0.49
    GIVEREF
    0.49
    Act Density 7.699%

    No Known Activations