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

    Neuronpedia

    INDEX
    Explanations

    Apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pazar
    -0.07
    가지
    -0.07
     сосед
    -0.06
     Veronica
    -0.06
    оян
    -0.06
    _AURA
    -0.06
     Vegan
    -0.06
    řik
    -0.06
     یعنی
    -0.06
    .matmul
    -0.06
    POSITIVE LOGITS
     Ports
    0.07
    .Android
    0.07
     powers
    0.06
    лу
    0.06
     Description
    0.06
    Men
    0.06
     
    0.06
     constructed
    0.06
     транспор
    0.06
    059
    0.06
    Act Density 0.001%

    No Known Activations