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

    Neuronpedia

    INDEX
    Explanations

    marking a foundation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חו
    1.34
    дова
    1.24
    There
    1.21
    jest
    1.21
    le
    1.16
    बाज
    1.15
     There
    1.12
     Lemma
    1.12
    தொ
    1.11
     初
    1.10
    POSITIVE LOGITS
     vielfält
    1.70
     autént
    1.63
     poucos
    1.60
    खाव
    1.60
    ໂດຍ
    1.54
     gewisse
    1.52
     vielf
    1.52
     noget
    1.51
     véritables
    1.48
    োঁয়া
    1.47
    Act Density 0.117%

    No Known Activations