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

    Neuronpedia

    INDEX
    Explanations

    получа я, might enjoy, one alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ires
    0.47
     Premium
    0.47
    -【
    0.45
    ensation
    0.45
    Her
    0.44
    premium
    0.43
     Her
    0.43
    azone
    0.43
    Zip
    0.43
    isk
    0.42
    POSITIVE LOGITS
     chứng
    0.49
    м
    0.48
    wpilibj
    0.47
     când
    0.46
     còn
    0.45
    리와
    0.45
    ोनेशिया
    0.44
    运作
    0.44
    お届け
    0.44
     зрения
    0.44
    Act Density 0.000%

    No Known Activations