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

    Neuronpedia

    INDEX
    Explanations

    random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    प्रिय
    -0.07
    hm
    -0.07
     hemisphere
    -0.07
     meant
    -0.07
     parent
    -0.07
     छुट
    -0.07
    prim
    -0.06
    .reshape
    -0.06
     hon
    -0.06
    POSITIVE LOGITS
     rápidamente
    0.11
     rapidamente
    0.11
     становится
    0.11
    成为
    0.10
     rapidement
    0.10
     يصبح
    0.10
    了吗
    0.10
     becomes
    0.10
     quickly
    0.10
    になる
    0.10
    Act Density 0.329%
    No Known Activations