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

    Neuronpedia

    INDEX
    Explanations

    language learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recycle
    -0.09
     destroy
    -0.08
    Detach
    -0.08
     पुन
    -0.08
     Metals
    -0.08
     verniet
    -0.08
    ेश्य
    -0.08
     reuse
    -0.08
     wrench
    -0.08
     exhaustion
    -0.08
    POSITIVE LOGITS
     biling
    0.08
     재미
    0.08
     beginner
    0.08
     hobbies
    0.08
     공부
    0.08
     숙
    0.08
     знаком
    0.08
    /blog
    0.08
     möglichst
    0.08
     温
    0.08
    Act Density 0.016%

    No Known Activations