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

    Neuronpedia

    INDEX
    Explanations

    you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तुम्ही
    0.42
    จำเป็น
    0.41
     அவசியம்
    0.39
    glicherweise
    0.37
     potete
    0.36
    مكن
    0.35
     প্রয়োজনীয়
    0.35
     सकेगा
    0.35
    AnyCPU
    0.34
     getattr
    0.34
    POSITIVE LOGITS
     want
    3.52
    Want
    3.25
     Want
    3.23
    want
    3.19
     muốn
    3.16
     wants
    3.14
     wanting
    3.06
     ingin
    2.97
     wanted
    2.88
    想要
    2.77
    Act Density 0.407%

    No Known Activations