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

    Neuronpedia

    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     열
    -0.06
    놓
    -0.06
     vagina
    -0.06
    煤
    -0.06
     chores
    -0.06
     TSA
    -0.06
    xab
    -0.06
     що
    -0.06
     McN
    -0.06
    POSITIVE LOGITS
     perpetrated
    0.07
    О
    0.07
    .archive
    0.06
     solar
    0.06
     Wonderful
    0.06
    .maps
    0.06
    Tests
    0.06
     dealership
    0.06
     practices
    0.06
     prohibiting
    0.06
    Act Density 0.006%

    No Known Activations