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

    Neuronpedia

    INDEX
    Explanations

    will use for datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arms
    0.43
    nesses
    0.43
    wv
    0.42
    mnu
    0.41
    ស្រាយ
    0.40
    sempel
    0.40
    hv
    0.40
    mmol
    0.39
    嵌入
    0.39
    ahari
    0.39
    POSITIVE LOGITS
     serán
    0.53
     conceitos
    0.52
     será
    0.51
     utilisez
    0.51
     piezo
    0.50
     cung
    0.50
     serão
    0.50
     החד
    0.50
     være
    0.49
     fara
    0.49
    Act Density 0.000%

    No Known Activations