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

    Neuronpedia

    INDEX
    Explanations

    advertising/marketing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plat
    -0.07
     ginger
    -0.07
     uphill
    -0.07
    iddleware
    -0.07
    pegawai
    -0.06
     quotations
    -0.06
     McConnell
    -0.06
    -free
    -0.06
    -platform
    -0.06
    سط
    -0.06
    POSITIVE LOGITS
    まず
    0.06
     gần
    0.06
     Sir
    0.06
     Bengals
    0.06
    ійно
    0.06
    	trace
    0.05
    mor
    0.05
    ;"><?
    0.05
     Sem
    0.05
    После
    0.05
    Act Density 0.209%

    No Known Activations