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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly apostrophes, and specific counts or tags

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.43
    NamedQueries
    -0.40
    endregion
    -0.37
     cedo
    -0.34
    MigrationBuilder
    -0.34
     dalamnya
    -0.33
    importanza
    -0.32
    /*
    -0.30
    dataclass
    -0.30
    bildēt
    -0.30
    POSITIVE LOGITS
     dezelve
    0.55
     queſta
    0.51
    ScopeManager
    0.51
    majánló
    0.50
     ſind
    0.49
    󠁣
    0.48
     ſche
    0.47
     citrate
    0.47
     mac
    0.47
    httphttps
    0.46
    Act Density 0.148%

    No Known Activations