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

    Neuronpedia

    INDEX
    Explanations

    is important, only, or vital

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acompanhar
    0.52
     escuchar
    0.52
    சையில்
    0.50
    േഷ
    0.50
    REGEX
    0.49
    ILI
    0.49
    ̣ng
    0.48
    штар
    0.47
    觓
    0.47
     marginTop
    0.47
    POSITIVE LOGITS
     dirt
    0.54
     rodent
    0.51
    R
    0.51
    Del
    0.50
    س
    0.49
     property
    0.49
     postulate
    0.49
     প্রকৌশ
    0.46
    Life
    0.45
     phosphate
    0.45
    Act Density 0.000%

    No Known Activations