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

    Neuronpedia

    INDEX
    Explanations

    explaining a solution or secret

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     நடிக்க
    0.69
     billowing
    0.66
     وهذا
    0.65
    uta
    0.64
    িস
    0.64
     despise
    0.64
    崔
    0.64
     ditemukan
    0.63
    ্য
    0.63
     voulu
    0.61
    POSITIVE LOGITS
    er
    0.82
     След
    0.81
    ท์
    0.79
    l
    0.79
    ﺭ
    0.79
    auml
    0.74
    hdu
    0.73
    紶
    0.71
    Когда
    0.71
    thedocs
    0.70
    Act Density 0.005%

    No Known Activations