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

    Neuronpedia

    INDEX
    Explanations

    instances of someone being accused of something, or suspecting something

    oai_token-act-pair · gemini-2.0-flash

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.67
    +#+#
    -0.65
     Paglinawan
    -0.65
    SequentialGroup
    -0.59
    談社
    -0.59
    LookAnd
    -0.58
     Baillargeon
    -0.57
    AndEndTag
    -0.56
    -0.56
    FormTagHelper
    -0.54
    POSITIVE LOGITS
     accuse
    0.96
     suspected
    0.92
     accusations
    0.91
     accused
    0.91
     accuses
    0.85
     accusation
    0.84
     suspect
    0.82
     suspects
    0.82
     accusing
    0.81
     allegations
    0.78
    Act Density 0.642%

    No Known Activations