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

    Neuronpedia

    INDEX
    Explanations

    serving

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinsim
    0.37
    umap
    0.37
     محفوظ
    0.36
    ٹن
    0.36
     約
    0.35
     عنه
    0.35
    焯
    0.35
    NEY
    0.35
    Armstrong
    0.35
     عنها
    0.35
    POSITIVE LOGITS
     served
    0.45
     serving
    0.44
     ල
    0.41
    Serving
    0.41
     Lakers
    0.40
     Given
    0.39
     servir
    0.39
     abatement
    0.39
    ative
    0.39
     Serving
    0.38
    Act Density 0.000%

    No Known Activations