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

    Neuronpedia

    INDEX
    Explanations

    X-ray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πέ
    -0.09
     chants
    -0.09
     Pillow
    -0.09
     rein
    -0.08
     hemp
    -0.08
     speech
    -0.08
     curricular
    -0.08
    cloth
    -0.08
     Slack
    -0.08
    speech
    -0.08
    POSITIVE LOGITS
    -rays
    0.10
    -ray
    0.10
    -Ray
    0.10
     emission
    0.09
    Neu
    0.08
    小说
    0.08
    .parse
    0.08
    Casino
    0.08
     brightest
    0.08
     bright
    0.08
    Act Density 0.003%

    No Known Activations