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

    Neuronpedia

    INDEX
    Explanations

    encoder and decoder architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ഈ
    0.43
     propagated
    0.42
     também
    0.42
     forsk
    0.41
    笉
    0.41
    ফেট
    0.41
     pfl
    0.41
    ")/
    0.40
    ましたが
    0.39
     juga
    0.39
    POSITIVE LOGITS
    Shel
    0.44
    Rew
    0.42
    remainder
    0.42
    Evalu
    0.42
    Unt
    0.41
    Evaluation
    0.40
    planet
    0.40
    Oriental
    0.40
    ponent
    0.40
    Creator
    0.40
    Act Density 0.001%

    No Known Activations