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

    Neuronpedia

    INDEX
    Explanations

    explaining algorithm functionalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இன்னொரு
    0.81
    Innen
    0.76
     belki
    0.72
    みたいな
    0.72
     ligados
    0.70
     czasem
    0.69
     parfois
    0.69
     Liaison
    0.69
    裡面
    0.68
     maybe
    0.68
    POSITIVE LOGITS
    하였다
    1.05
    >.</
    1.05
     functionalities
    1.02
    이며
    1.02
     enjoyable
    0.99
    操作
    0.98
    💹
    0.98
    하였
    0.98
    🏪
    0.97
    🌓
    0.97
    Act Density 0.276%

    No Known Activations