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

    Neuronpedia

    INDEX
    Explanations

    not aligning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inh
    0.37
     ""`
    0.32
     processi
    0.30
     whatnot
    0.30
     প্রভৃতি
    0.29
    ult
    0.29
    相互
    0.29
     Chúng
    0.29
    することも
    0.29
    cz
    0.29
    POSITIVE LOGITS
     সিনেমায়
    0.39
     cinemas
    0.36
    남자
    0.36
     남자
    0.35
     футболка
    0.35
     муж
    0.35
    ➛
    0.34
     katol
    0.34
     படத்தில்
    0.34
     میکنم
    0.34
    Act Density 0.036%

    No Known Activations