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

    Neuronpedia

    INDEX
    Explanations

    statistical data contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appreciably
    0.46
     perturbed
    0.42
    着急
    0.41
    แค
    0.39
    PERT
    0.39
    囫
    0.38
     其中
    0.38
    ער
    0.37
    ವರ್
    0.37
     المصري
    0.37
    POSITIVE LOGITS
     contributions
    0.46
    Contributions
    0.46
     Beitrag
    0.44
     CONTRIBUT
    0.42
     contribution
    0.41
     contribute
    0.41
    貢献
    0.41
     contribu
    0.40
     contributo
    0.40
     freeze
    0.40
    Act Density 0.000%

    No Known Activations