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

    Neuronpedia

    INDEX
    Explanations

    best option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amount
    0.45
     вариант
    0.44
     possible
    0.44
     fidelity
    0.43
     proven
    0.43
     explanation
    0.43
    kow
    0.43
     possibile
    0.42
     combinação
    0.42
     combination
    0.42
    POSITIVE LOGITS
     PARTICULAR
    0.42
     Fit
    0.41
     therein
    0.41
    របស់
    0.39
    某种
    0.39
     hereof
    0.39
     hina
    0.39
     fit
    0.39
    的重要
    0.38
    質問
    0.37
    Act Density 0.010%

    No Known Activations