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

    Neuronpedia

    INDEX
    Explanations

    preposition following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ப்பட்டுள்ள
    0.37
     defraud
    0.37
    arının
    0.37
    ونکو
    0.36
     खुलने
    0.36
    लिसा
    0.35
     রহমানকে
    0.35
    უს
    0.35
    ើស
    0.35
    ibrated
    0.35
    POSITIVE LOGITS
    、
    0.54
    ®,
    0.43
    ,
    0.43
     etc
    0.42
    ،
    0.41
    、「
    0.40
    ™,
    0.38
    ²,
    0.38
    부터
    0.38
    (),
    0.37
    Act Density 0.000%

    No Known Activations