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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons or measurements

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

    best or highest values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opsida
    -0.60
    __*/
    -0.56
     invokingState
    -0.55
    SequentialGroup
    -0.52
    WindowConstants
    -0.51
    ViewInit
    -0.45
    Demografie
    -0.44
     الرياضيه
    -0.44
    LocalizedString
    -0.43
    ectoria
    -0.42
    POSITIVE LOGITS
    Maximum
    0.63
    maximum
    0.61
     Maximum
    0.60
     maximum
    0.57
    MAXIMUM
    0.54
     MAXIMUM
    0.52
    Highest
    0.51
    的最大
    0.50
    highest
    0.49
     highest
    0.48
    Act Density 0.124%

    No Known Activations