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

    Neuronpedia

    INDEX
    Explanations

    greatest joy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Planet
    0.44
    WERS
    0.42
     cottura
    0.42
    ্রি
    0.42
     amplo
    0.42
     thermoplastic
    0.41
     lze
    0.40
     veloce
    0.40
     ambiance
    0.40
     plains
    0.40
    POSITIVE LOGITS
    对我
    0.45
     আমাকে
    0.43
    和我
    0.42
    让我
    0.42
     моей
    0.42
     माझ्या
    0.41
     मेरे
    0.41
    きっかけ
    0.41
     overjoyed
    0.40
     miei
    0.39
    Act Density 0.000%

    No Known Activations