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

    Neuronpedia

    INDEX
    Explanations

    Marilyn Monroe or restrictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਨ
    0.62
    in
    0.59
    ن
    0.51
    l
    0.46
    री
    0.46
    ని
    0.45
    ini
    0.45
    मन
    0.44
    جز
    0.43
    पी
    0.43
    POSITIVE LOGITS
    됬
    0.54
     mila
    0.51
    銨
    0.51
     заключения
    0.50
     možno
    0.50
    둰
    0.50
     nghe
    0.49
     neemt
    0.49
    чення
    0.49
     potrebbe
    0.49
    Act Density 0.000%

    No Known Activations