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

    Neuronpedia

    INDEX
    Explanations

    a variety of common words, especially in the context of lists or groups of things relating to specific topics.

    oai_token-act-pair · gemini-2.0-flash

    "followed"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EdgeInsets
    -0.55
    expandindo
    -0.54
    INCLUDED
    -0.52
    Tikang
    -0.50
    AnchorStyles
    -0.49
     Alors
    -0.49
    tvguidetime
    -0.48
    luci
    -0.45
    LEncoder
    -0.45
    énération
    -0.45
    POSITIVE LOGITS
     followed
    2.73
    followed
    2.34
     Followed
    2.27
     seguido
    2.00
    Followed
    1.94
     suivie
    1.89
     diikuti
    1.59
     seguida
    1.52
     suivi
    1.35
     gevol
    1.33
    Act Density 7.563%

    No Known Activations