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

    Neuronpedia

    INDEX
    Explanations

    features related to vehicle design and aesthetics

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

    describing quality

    np_acts-logits-general · gemini-2.0-flash

    striking, dynamic, assertive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.71
     shitty
    -0.63
    hyrchwyd
    -0.63
    RegressionTest
    -0.63
     ProtoMessage
    -0.62
     estekak
    -0.62
     $_(
    -0.62
    ]")]
    -0.61
     googling
    -0.60
     disambiguazione
    -0.59
    POSITIVE LOGITS
     exquisite
    0.44
     immerse
    0.44
     refined
    0.41
     exceptional
    0.41
     unique
    0.40
     inspired
    0.39
     dynamic
    0.38
     striking
    0.38
     selected
    0.37
     immersed
    0.37
    Act Density 0.213%

    No Known Activations