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

    Neuronpedia

    INDEX
    Explanations

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     אַ
    0.37
     však
    0.34
    Ú
    0.34
    }$-(
    0.33
     вопроса
    0.32
     impermeable
    0.32
     porém
    0.32
    اسم
    0.31
    ÈRE
    0.31
    ROWS
    0.31
    POSITIVE LOGITS
    以及
    0.42
     तसेच
    0.40
     以及
    0.39
     oraz
    0.39
     Additionally
    0.38
     separately
    0.38
     نیز
    0.37
    また
    0.37
     Ayrıca
    0.36
     وكذلك
    0.36
    Act Density 0.118%

    No Known Activations