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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yeni
    -0.06
     Lonely
    -0.06
     textual
    -0.06
    ()<<
    -0.06
     собою
    -0.06
    rimp
    -0.06
     Classe
    -0.05
    %p
    -0.05
    entionPolicy
    -0.05
     flagged
    -0.05
    POSITIVE LOGITS
    产
    0.07
    ankan
    0.07
    vironment
    0.06
    егодня
    0.06
     challenge
    0.06
     الش
    0.06
    ivia
    0.06
     dismissal
    0.06
    cela
    0.06
    _CN
    0.06
    Act Density 0.073%

    No Known Activations