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

    Neuronpedia

    INDEX
    Explanations

    how things influence outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getNome
    0.47
    azz
    0.45
     contagious
    0.42
     Melhor
    0.42
     Magnet
    0.42
    hematic
    0.41
     স্মৃতি
    0.41
     nakk
    0.40
     मतदान
    0.40
     Ajust
    0.40
    POSITIVE LOGITS
    َت
    0.48
     thẩm
    0.44
     sonucu
    0.43
     jugs
    0.42
     findings
    0.41
    গ
    0.41
    的服务
    0.41
     espon
    0.41
    ୈ
    0.40
    ୱ
    0.40
    Act Density 0.002%

    No Known Activations