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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behind
    -0.07
    /per
    -0.07
    'in
    -0.06
     Nisan
    -0.06
    ,'']]],↵
    -0.06
     mostr
    -0.06
     دارند
    -0.06
    のみ
    -0.06
    _PAIR
    -0.06
    制度
    -0.06
    POSITIVE LOGITS
    	mod
    0.06
     них
    0.06
    .qty
    0.06
    .getAll
    0.06
     submarines
    0.06
    τις
    0.06
     Vintage
    0.06
    .commit
    0.06
     modern
    0.06
     COVID
    0.06
    Act Density 0.029%

    No Known Activations