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

    Neuronpedia

    INDEX
    Explanations

    conclusion and summary phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strictly
    0.36
    তিক্রম
    0.32
     bes
    0.31
     merc
    0.31
     corresponding
    0.31
    fraction
    0.31
    hose
    0.31
     fraction
    0.31
    ън
    0.31
     Zusätzlich
    0.31
    POSITIVE LOGITS
     tehát
    0.53
     While
    0.50
    While
    0.48
    Mientras
    0.43
    虽然
    0.40
     Mientras
    0.38
     resultArray
    0.38
     мушка
    0.38
     THINK
    0.38
    ╿
    0.38
    Act Density 0.010%

    No Known Activations