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

    Neuronpedia

    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -1.18
    Personensuche
    -1.14
    parsedMessage
    -1.13
     Roskov
    -1.07
     Савезне
    -1.03
     Мексичка
    -1.00
     مرئيه
    -0.96
     étoit
    -0.96
     feroit
    -0.96
     auroit
    -0.95
    POSITIVE LOGITS
     –
    0.46
     advanced
    0.38
    –
    0.38
    :
    0.37
    ast
    0.36
     modern
    0.35
     usual
    0.35
     P
    0.35
     :
    0.35
    ta
    0.34
    Act Density 0.023%

    No Known Activations