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

    Neuronpedia

    INDEX
    Explanations

    categories and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    と考えて
    0.47
    Cite
    0.44
    SOCK
    0.44
    도를
    0.43
    ほどの
    0.43
    션을
    0.43
    برى
    0.43
    传感
    0.42
    대의
    0.42
     Polarization
    0.42
    POSITIVE LOGITS
     bambino
    0.49
    ley
    0.48
    เรื่อง
    0.47
     karakter
    0.45
     is
    0.45
    born
    0.45
    बच्चों
    0.44
     euh
    0.43
    子ども
    0.43
     fundamental
    0.43
    Act Density 0.003%

    No Known Activations