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

    Neuronpedia

    INDEX
    Explanations

    medical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	add
    -0.07
     dissoci
    -0.06
     cevap
    -0.06
     Romney
    -0.06
     ガ
    -0.06
     BG
    -0.06
    /g
    -0.06
     Confeder
    -0.06
     RD
    -0.06
    Yesterday
    -0.06
    POSITIVE LOGITS
    िलत
    0.07
    bis
    0.07
    -addons
    0.07
    Merc
    0.06
     aider
    0.06
    ADOS
    0.06
    _does
    0.06
     Regardless
    0.06
     ofs
    0.06
    elsinki
    0.06
    Act Density 0.011%

    No Known Activations