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

    Neuronpedia

    INDEX
    Explanations

    familiarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ік
    -0.06
    acho
    -0.06
    urrenc
    -0.06
     напря
    -0.06
    重複
    -0.06
     né
    -0.06
    source
    -0.06
    ской
    -0.06
    ****************************************************************
    -0.06
    atus
    -0.06
    POSITIVE LOGITS
    **,
    0.07
    яет
    0.07
    -media
    0.07
     فر
    0.06
    	common
    0.06
    escaping
    0.06
    (sm
    0.06
     absolute
    0.06
     Democrats
    0.06
    nilai
    0.06
    Act Density 0.024%

    No Known Activations