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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increasing
    -0.07
    Fight
    -0.07
    @student
    -0.06
     acomp
    -0.06
    ForResource
    -0.06
    	data
    -0.06
    /course
    -0.06
     Hispan
    -0.06
    다는
    -0.06
    ський
    -0.06
    POSITIVE LOGITS
    ',
    0.06
    _ETH
    0.06
    426
    0.06
    onavir
    0.06
    ITCH
    0.06
    OUNDS
    0.06
    िप
    0.06
    pun
    0.06
    	assertTrue
    0.06
    िसस
    0.06
    Act Density 0.008%

    No Known Activations