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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躁
    0.39
    硃
    0.36
    industrial
    0.36
    Ante
    0.35
    ದಿ
    0.35
    urre
    0.34
     ileti
    0.34
     निदेश
    0.34
     cruelty
    0.34
     automotive
    0.34
    POSITIVE LOGITS
     ক্লাব
    0.42
     комплек
    0.40
     mês
    0.40
    Club
    0.39
     Club
    0.39
     subir
    0.39
     gesprek
    0.38
     خر
    0.38
    Endereco
    0.37
     endereco
    0.37
    Act Density 0.063%

    No Known Activations