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

    Neuronpedia

    INDEX
    Explanations

    Sentence snippets with punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unprocessable
    -0.07
     cùng
    -0.07
     CET
    -0.07
    尚
    -0.07
     revolves
    -0.06
     Este
    -0.06
     ник
    -0.06
    ์)
    -0.06
     round
    -0.06
    (DbContext
    -0.06
    POSITIVE LOGITS
    tır
    0.06
    nants
    0.06
     fabrics
    0.06
    legal
    0.06
     anime
    0.06
     σύν
    0.06
    Як
    0.06
     Snake
    0.06
    Media
    0.06
     hallway
    0.06
    Act Density 0.001%

    No Known Activations