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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τιν
    -0.07
     monitored
    -0.07
     footprint
    -0.07
    _kv
    -0.06
    _follow
    -0.06
     beforehand
    -0.06
     within
    -0.06
    crime
    -0.06
     fi
    -0.06
    Tex
    -0.06
    POSITIVE LOGITS
     ese
    0.07
     prenatal
    0.07
     icing
    0.06
    tha
    0.06
    ้เป
    0.06
     listens
    0.06
    (ix
    0.06
     klub
    0.06
    =form
    0.06
    ’.↵↵
    0.06
    Act Density 0.001%

    No Known Activations