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

    Neuronpedia

    INDEX
    Explanations

    scientific terms with the prefix "auto" or the suffix "hagic" as well as the word "associated"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.85
     Majefty
    -0.85
    hilt
    -0.80
     Majesté
    -0.79
     nakalista
    -0.79
     disambiguazione
    -0.79
    AnchorTagHelper
    -0.77
    URLException
    -0.76
    MessageTagHelper
    -0.75
     Monfieur
    -0.74
    POSITIVE LOGITS
     autophagy
    1.52
    hagy
    1.20
     autop
    0.94
     Autop
    0.81
    autop
    0.68
    hagic
    0.65
    itäts
    0.60
     Hara
    0.57
    ]")]
    0.55
     asse
    0.53
    Act Density 0.001%

    No Known Activations