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

    Neuronpedia

    INDEX
    Explanations

    unk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrived
    -0.07
     Gabri
    -0.06
     Plan
    -0.06
    �
    -0.06
     FAA
    -0.06
    	new
    -0.06
     oxid
    -0.06
     accommodation
    -0.06
    Staff
    -0.06
    ilent
    -0.06
    POSITIVE LOGITS
    adoop
    0.10
    gger
    0.08
    What
    0.08
    	spec
    0.07
     उत
    0.07
    dera
    0.07
     Architects
    0.07
    �
    0.07
     lorem
    0.07
     What
    0.06
    Act Density 0.006%

    No Known Activations