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

    Neuronpedia

    INDEX
    Explanations

    necessity expressed after pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ലാണ്
    0.39
     পছন্দের
    0.37
    션을
    0.36
    怅
    0.35
    లుగా
    0.35
    ቱን
    0.35
    multicolumn
    0.34
    𝒈
    0.34
    旿
    0.34
    प्ताह
    0.33
    POSITIVE LOGITS
     need
    2.88
     нужда
    2.75
    需要
    2.73
     besoin
    2.69
     potrzeb
    2.67
     needing
    2.64
    need
    2.61
     نیاز
    2.61
     Need
    2.58
     cần
    2.53
    Act Density 0.041%

    No Known Activations