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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /TR
    -0.07
     bunları
    -0.07
     BC
    -0.07
     ceased
    -0.07
    _sms
    -0.07
     araç
    -0.06
    mesine
    -0.06
    capture
    -0.06
     Duo
    -0.06
    ranges
    -0.06
    POSITIVE LOGITS
     intend
    0.07
     anticipated
    0.06
     Indust
    0.06
     incredibly
    0.06
     broadcaster
    0.06
    liked
    0.06
     Lah
    0.06
    bb
    0.06
     ModelAndView
    0.06
     行
    0.06
    Act Density 0.006%

    No Known Activations