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

    Neuronpedia

    INDEX
    Explanations

    UI building frameworks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abych
    -0.07
     randint
    -0.06
    ponential
    -0.06
     Palin
    -0.06
    survey
    -0.06
    jc
    -0.06
    Things
    -0.06
    地下
    -0.06
    vine
    -0.06
    Boundary
    -0.06
    POSITIVE LOGITS
     demonstrations
    0.07
     orderId
    0.06
     coer
    0.06
     SEA
    0.06
    .Val
    0.06
    FileVersion
    0.06
    _transfer
    0.06
    更加
    0.06
    �
    0.06
    THON
    0.06
    Act Density 0.024%

    No Known Activations