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

    Neuronpedia

    INDEX
    Explanations

    metaphors and analogies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سك
    -0.08
     gam
    -0.07
     serif
    -0.07
    Filename
    -0.07
    Pilot
    -0.07
     hurdles
    -0.07
    .times
    -0.07
     प्रतिक्र
    -0.07
     peruste
    -0.07
     deslig
    -0.07
    POSITIVE LOGITS
     analogy
    0.13
     metaphor
    0.12
    ovit
    0.09
    achtige
    0.09
    -shaped
    0.09
     Krankheit
    0.09
    แห่ง
    0.08
    hu
    0.08
    ाकार
    0.08
    analog
    0.08
    Act Density 0.064%

    No Known Activations