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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and single quotes

    oai_token-act-pair · gemini-2.0-flash

    Single quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    着
    -0.49
    Cer
    -0.43
     Cer
    -0.42
    盘
    -0.42
     d
    -0.40
    sp
    -0.40
    ord
    -0.39
     Sp
    -0.38
    架
    -0.36
    Sp
    -0.36
    POSITIVE LOGITS
     surla
    1.12
    Personendaten
    0.94
    InitVars
    0.89
     ModelExpression
    0.89
    RuleContext
    0.88
    Vidite
    0.88
     gynhyrchwyd
    0.87
    esez
    0.85
     चीज़ों
    0.84
     itſelf
    0.84
    Act Density 0.294%

    No Known Activations