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

    Neuronpedia

    INDEX
    Explanations

    food ingredients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ваем
    -0.06
     Friedman
    -0.06
    nees
    -0.06
     Secondly
    -0.06
    гає
    -0.06
    owski
    -0.06
     edad
    -0.06
     SPE
    -0.06
     foreigners
    -0.06
    SO
    -0.06
    POSITIVE LOGITS
     trig
    0.07
     establishing
    0.07
     Decorating
    0.07
     getattr
    0.07
     establish
    0.07
     reshape
    0.07
     fashioned
    0.07
     __
    0.07
     equiv
    0.07
     Shaft
    0.06
    Act Density 0.020%

    No Known Activations