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

    Neuronpedia

    INDEX
    Explanations

    Plurals/verb conjugations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ぞ
    -0.07
     particul
    -0.07
     dále
    -0.07
     definitely
    -0.06
     Schmidt
    -0.06
     더욱
    -0.06
     literally
    -0.06
     من
    -0.06
     Automobile
    -0.06
    (gray
    -0.06
    POSITIVE LOGITS
    ing
    0.07
     함
    0.06
    s
    0.06
    ed
    0.06
    нед
    0.06
    $$$
    0.06
    าย
    0.06
    support
    0.06
    aria
    0.06
    �
    0.06
    Act Density 0.125%

    No Known Activations