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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to dependence and decisions

    oai_token-act-pair · gemini-2.0-flash

    depends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numerusform
    -0.70
    -0.69
    IRMED
    -0.66
    expandindo
    -0.66
    InjectAttribute
    -0.64
    󠁢
    -0.63
     TextAppearance
    -0.63
     Gai
    -0.63
     оригіналу
    -0.61
     مشين
    -0.60
    POSITIVE LOGITS
     depends
    0.71
     depending
    0.68
     dipende
    0.65
    IActionResult
    0.64
     whether
    0.64
     zależ
    0.63
    depends
    0.63
     depended
    0.63
     depende
    0.59
     Depends
    0.59
    Act Density 1.120%

    No Known Activations