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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to electrical or semiconductor devices

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

    "Method" or "provided" followed by "a"

    np_acts-logits-general · gemini-2.0-flash

    provided a method of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.61
    roxene
    -0.53
     vicina
    -0.52
     Paglinawan
    -0.50
     ordinaires
    -0.49
    formik
    -0.48
     magari
    -0.48
    Vidite
    -0.47
     traditionnels
    -0.47
    равда
    -0.45
    POSITIVE LOGITS
     method
    0.98
     Method
    0.94
    Method
    0.84
    method
    0.76
     METHOD
    0.74
    METHOD
    0.74
     methods
    0.72
     méthode
    0.71
     método
    0.71
     Methods
    0.67
    Act Density 0.505%

    No Known Activations