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

    Neuronpedia

    INDEX
    Explanations

    section, file path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    复
    0.45
    桉
    0.40
    गल
    0.39
    學習
    0.39
    castellan
    0.38
     tég
    0.38
     संगठ
    0.37
    Elater
    0.37
     учеб
    0.37
    agia
    0.37
    POSITIVE LOGITS
    থি
    0.37
     percent
    0.36
     Marl
    0.36
     Percent
    0.35
     poked
    0.34
    Jf
    0.34
    luft
    0.34
     air
    0.33
    insi
    0.33
    panies
    0.32
    Act Density 0.029%

    No Known Activations