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

    Neuronpedia

    INDEX
    Explanations

    future or repeat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如果你
    0.45
     최고의
    0.44
    Earnings
    0.44
    ⤠
    0.44
     మీరు
    0.44
     하루
    0.43
    డే
    0.43
    하루
    0.42
    你应该
    0.42
    Anyone
    0.42
    POSITIVE LOGITS
     भविष्य
    0.71
     future
    0.70
     nächste
    0.69
    次回
    0.67
    下次
    0.65
     Zukunft
    0.63
     repeat
    0.59
     futuras
    0.59
     futuro
    0.56
     next
    0.55
    Act Density 0.099%

    No Known Activations