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

    Neuronpedia

    INDEX
    Explanations

    amount of money or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mnemonic
    0.66
     calcul
    0.65
     index
    0.64
    假設
    0.64
    ため
    0.63
    тся
    0.62
    规划
    0.60
    index
    0.59
     calculation
    0.57
    does
    0.57
    POSITIVE LOGITS
    ákat
    0.69
     allait
    0.65
    䞍
    0.64
     edizione
    0.64
    ﹞
    0.63
     رنگ
    0.63
    ܒ
    0.63
     пришлось
    0.62
     男女
    0.62
    ದ್ದು
    0.62
    Act Density 0.001%

    No Known Activations