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

    Neuronpedia

    INDEX
    Explanations

    word collocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Na
    0.44
    Na
    0.40
    quant
    0.38
     postul
    0.38
     cref
    0.37
     float
    0.36
     Creed
    0.36
     така
    0.36
     kredit
    0.36
     minha
    0.36
    POSITIVE LOGITS
     எனவே
    0.39
    AINLESS
    0.39
    獬
    0.39
     மூன்றாவது
    0.38
    বৃত্ত
    0.37
    የ
    0.37
    ప్ర
    0.37
    按钮
    0.37
     អ្នក
    0.36
    Telex
    0.36
    Act Density 0.002%

    No Known Activations