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

    Neuronpedia

    INDEX
    Explanations

    punctuation and commas within text

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

    error messages and filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embassies
    -0.63
     propOrder
    -0.59
     Embassy
    -0.58
     ब्रेकडाउन
    -0.57
     HasFactory
    -0.54
     embassy
    -0.54
     typelib
    -0.50
    Personendaten
    -0.50
     diplomats
    -0.48
    tyk
    -0.48
    POSITIVE LOGITS
    argout
    0.40
    0.39
    +#+#
    0.37
    istoitu
    0.35
    endmodule
    0.34
    ScopeManager
    0.33
     שוליים
    0.32
     Wh
    0.32
    ẩm
    0.32
     egli
    0.31
    Act Density 0.010%

    No Known Activations