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

    Neuronpedia

    INDEX
    Explanations

    about specific moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asmine
    0.45
    although
    0.43
    但是
    0.42
    BYTE
    0.41
    ில்லை
    0.40
    حمد
    0.39
    明
    0.39
    ൦
    0.38
    Petit
    0.38
    眎
    0.38
    POSITIVE LOGITS
     betterment
    0.52
     ایسے
    0.50
     relevante
    0.48
    对其
    0.48
    それを
    0.47
     relevancia
    0.47
     populace
    0.46
     relevantes
    0.45
     mejoras
    0.44
     RE
    0.44
    Act Density 0.016%

    No Known Activations