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

    Neuronpedia

    INDEX
    Explanations

    protein and dish names☇

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍪
    0.77
     waivers
    0.72
    饴
    0.72
    hedra
    0.71
     Telegram
    0.71
     Hadamard
    0.69
     Babel
    0.69
     MNIST
    0.68
     wavefunction
    0.68
     metastability
    0.67
    POSITIVE LOGITS
     chicken
    2.40
     Chicken
    2.25
    Chicken
    2.14
    chicken
    2.04
     poultry
    1.77
     pollo
    1.75
     shrimp
    1.73
     steak
    1.72
     Shrimp
    1.63
     चिकन
    1.62
    Act Density 0.511%

    No Known Activations