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

    Neuronpedia

    INDEX
    Explanations

    expressions and descriptions related to quality and excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive adjectives

    np_acts-logits-general · gemini-2.0-flash

    evaluative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.94
    حياته
    -0.80
     تضيفلها
    -0.78
    WriteTagHelper
    -0.74
     zelve
    -0.73
     للمعارف
    -0.73
     AssemblyCulture
    -0.72
     anún
    -0.71
    seamnă
    -0.71
     zoude
    -0.70
    POSITIVE LOGITS
    !
    0.81
     for
    0.74
    ,
    0.72
    .
    0.70
     because
    0.70
     as
    0.70
     to
    0.70
     but
    0.69
     in
    0.68
    ly
    0.63
    Act Density 0.482%

    No Known Activations