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

    Neuronpedia

    INDEX
    Explanations

    ideal, preferred, or recommended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    正しい
    0.39
    ুনের
    0.38
    ብር
    0.38
     prawidł
    0.37
     sbagli
    0.37
     mussten
    0.37
     করি
    0.36
     richtigen
    0.36
    umbers
    0.36
     colitis
    0.36
    POSITIVE LOGITS
     ideally
    1.72
     желательно
    1.72
     preferably
    1.71
     Ideally
    1.66
     Preferably
    1.59
    Ideally
    1.55
    preferably
    1.49
     preferable
    1.45
     desirable
    1.32
     idéal
    1.23
    Act Density 0.024%

    No Known Activations