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

    Neuronpedia

    INDEX
    Explanations

    conjunctions introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    怎么办
    0.49
    où
    0.49
     examples
    0.47
    เพราะ
    0.46
    哪里
    0.45
     کجا
    0.45
     रहें
    0.44
     cui
    0.44
    prises
    0.44
     فه
    0.43
    POSITIVE LOGITS
     it
    0.86
     there
    0.86
     they
    0.76
     theres
    0.67
    there
    0.65
     their
    0.63
    それは
    0.60
    they
    0.56
     THEY
    0.56
     вони
    0.55
    Act Density 0.178%

    No Known Activations