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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기다
    -0.07
    ”
    -0.07
     kuk
    -0.07
    "
    -0.07
     Parts
    -0.06
    ")
    -0.06
     rugs
    -0.06
     CMP
    -0.06
     ambient
    -0.06
     textiles
    -0.06
    POSITIVE LOGITS
     Vanessa
    0.07
    Backend
    0.06
    (True
    0.06
    family
    0.06
     Fool
    0.06
    .optimizer
    0.06
    .Hide
    0.06
    thanks
    0.06
    .eval
    0.06
    mons
    0.06
    Act Density 0.023%

    No Known Activations