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

    Neuronpedia

    INDEX
    Explanations

    Medical/Scientific abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uzbek
    -0.07
    ewith
    -0.07
    elo
    -0.06
    Lake
    -0.06
     lane
    -0.06
     meal
    -0.06
     Terminator
    -0.06
    єш
    -0.06
     Rif
    -0.06
     сторін
    -0.06
    POSITIVE LOGITS
     طور
    0.07
    _quant
    0.07
    шим
    0.07
     spurred
    0.07
     。↵
    0.07
     д
    0.07
    —a
    0.07
    @s
    0.07
    !!↵
    0.07
    :E
    0.06
    Act Density 0.032%

    No Known Activations