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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oload
    -0.07
    eta
    -0.06
     zcela
    -0.06
     throat
    -0.06
     Languages
    -0.06
     Oven
    -0.06
    _histogram
    -0.06
    yun
    -0.06
    webElementProperties
    -0.06
    からない
    -0.06
    POSITIVE LOGITS
     FIRST
    0.07
     želez
    0.06
    _Pr
    0.06
    nutí
    0.06
     compliments
    0.06
     seamlessly
    0.06
     Silent
    0.06
    efore
    0.06
    Occup
    0.06
    }")↵
    0.06
    Act Density 0.221%

    No Known Activations