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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preference
    -0.07
    Gil
    -0.06
    	fi
    -0.06
    jm
    -0.06
     okul
    -0.06
    	all
    -0.06
    Russia
    -0.06
     гра
    -0.06
    ิง
    -0.06
     offen
    -0.06
    POSITIVE LOGITS
    collapse
    0.06
     hdr
    0.06
     kiss
    0.06
    _IDX
    0.06
    scape
    0.06
     peg
    0.06
    inations
    0.06
    ต
    0.06
    _release
    0.06
     الذه
    0.06
    Act Density 0.257%

    No Known Activations