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

    Neuronpedia

    INDEX
    Explanations

    the word "trust" in various contexts, especially legal ones

    oai_token-act-pair · gemini-2.0-flash

    trust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -1.18
    ContentAlignment
    -1.03
    MemoryWarning
    -1.03
    +#+#
    -1.01
    MLLoader
    -0.98
    IMPORTED
    -0.92
     ―――――
    -0.91
     $_"
    -0.90
     ་་
    -0.90
    \{\\
    -0.88
    POSITIVE LOGITS
     humains
    0.87
     démocr
    0.76
     chré
    0.75
     américains
    0.72
     sociaux
    0.71
     africains
    0.70
     chrétiens
    0.69
     alimentaires
    0.69
     communs
    0.69
     européens
    0.68
    Act Density 1.919%

    No Known Activations