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

    Neuronpedia

    INDEX
    Explanations

    _field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sass
    -0.07
    ɖ
    -0.07
    既然
    -0.07
     важ
    -0.07
     developments
    -0.07
    损害
    -0.06
    building
    -0.06
    .")↵↵
    -0.06
    不上
    -0.06
     necessarily
    -0.06
    POSITIVE LOGITS
     earth
    0.07
     These
    0.07
    tra
    0.07
     eagle
    0.07
    連續
    0.07
     shield
    0.06
    ия
    0.06
     yazı
    0.06
    荧
    0.06
    ┠
    0.06
    Act Density 0.004%

    No Known Activations