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

    Neuronpedia

    INDEX
    Explanations

    as introducing clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あるいは
    0.89
    Us
    0.87
    Namun
    0.85
    時候
    0.85
    Proposition
    0.82
    または
    0.81
    تے
    0.80
    If
    0.80
    もしくは
    0.79
    ब्रे
    0.79
    POSITIVE LOGITS
     there
    1.60
     it
    1.35
     they
    1.23
     we
    1.20
    there
    1.14
     이는
    1.12
     this
    1.08
     evidenced
    1.03
     vì
    1.01
     ഇത്
    1.01
    Act Density 0.046%

    No Known Activations