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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Context
    -0.06
     лит
    -0.06
     пла
    -0.06
     Kim
    -0.06
    Kim
    -0.06
     Jo
    -0.06
    άνει
    -0.06
    "H
    -0.06
    .Go
    -0.06
    _answers
    -0.06
    POSITIVE LOGITS
    _minor
    0.07
     altogether
    0.07
     horns
    0.06
     quelques
    0.06
     основном
    0.06
    мы
    0.06
     beyond
    0.06
    usher
    0.06
     beginning
    0.06
    EEP
    0.06
    Act Density 0.002%

    No Known Activations