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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal goals or aspirations

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

    Follows punctuation

    np_acts-logits-general · gemini-2.0-flash

    for this purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ījum
    -0.43
    ombra
    -0.42
    ционное
    -0.41
    crimin
    -0.39
    ̥
    -0.39
     wirklich
    -0.39
     Bár
    -0.39
    thor
    -0.38
     Bassi
    -0.38
    avit
    -0.37
    POSITIVE LOGITS
     Dafür
    1.39
    为此
    1.10
    Dazu
    1.03
     Dazu
    1.00
     daarvoor
    1.00
     >=",
    0.86
    そのため
    0.82
     defaultstate
    0.81
    ValueStyle
    0.81
    contentLoaded
    0.79
    Act Density 0.649%

    No Known Activations