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
     cot
    -0.07
     chairs
    -0.07
     hjem
    -0.07
     Chair
    -0.06
    GREE
    -0.06
    clare
    -0.06
    -suite
    -0.06
     suffix
    -0.06
     cargo
    -0.06
    Recorder
    -0.06
    POSITIVE LOGITS
     ¦
    0.08
     pornstar
    0.06
    .booking
    0.06
     filling
    0.06
     për
    0.06
    	new
    0.06
    мів
    0.06
     Nous
    0.06
     некоторых
    0.06
     ακό
    0.06
    Act Density 0.202%

    No Known Activations