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

    Neuronpedia

    INDEX
    Explanations

    __construct method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Princip
    0.45
    emu
    0.43
    princip
    0.41
     Princip
    0.40
     principals
    0.40
    ައް
    0.40
     Admittedly
    0.38
     rút
    0.38
    mittedly
    0.37
     bố
    0.37
    POSITIVE LOGITS
     അല്ലെങ്കിൽ
    0.42
     ওয়েবসাইটে
    0.41
     бюджета
    0.39
    ায়ণ
    0.38
     бюд
    0.37
    ƌ
    0.37
    垍
    0.36
     orçamento
    0.36
    <0xCE>
    0.36
     pinch
    0.36
    Act Density 0.000%

    No Known Activations