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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ربع
    -0.07
     사람
    -0.06
     наличие
    -0.06
    cole
    -0.06
     Assignment
    -0.06
    -Sah
    -0.06
    DATA
    -0.06
     Num
    -0.06
    	cnt
    -0.06
    .Val
    -0.06
    POSITIVE LOGITS
    maries
    0.07
    encoded
    0.07
     tossed
    0.07
    อาร
    0.06
    "><?=$
    0.06
    ‘s
    0.06
     captain
    0.06
    �
    0.06
     Федера
    0.06
    разд
    0.06
    Act Density 0.021%

    No Known Activations