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

    Neuronpedia

    INDEX
    Explanations

    Ryan & Deci theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通讯
    -0.09
     planes
    -0.08
    经
    -0.08
    无人
    -0.08
    北京
    -0.08
    _FROM
    -0.08
     Deutschlands
    -0.08
     darknet
    -0.08
    _CODE
    -0.08
     Germania
    -0.07
    POSITIVE LOGITS
     purpos
    0.09
     शरीर
    0.08
    ्या
    0.08
     Karen
    0.08
     aktivit
    0.08
    atom
    0.07
     siebie
    0.07
     удел
    0.07
     tubuh
    0.07
     jeg
    0.07
    Act Density 0.009%

    No Known Activations