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

    Neuronpedia

    INDEX
    Explanations

    constantly changing estimates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.52
    其他
    0.48
    char
    0.48
    fram
    0.46
    έ
    0.44
    κρι
    0.43
    d
    0.43
    ط
    0.42
    কীর
    0.42
    ionais
    0.41
    POSITIVE LOGITS
     substantially
    0.49
     proizvoda
    0.49
     yako
    0.47
     Poa
    0.46
     invoices
    0.46
     ಮತ
    0.45
     hectare
    0.45
     ntawm
    0.45
     	i
    0.44
     Request
    0.44
    Act Density 0.000%

    No Known Activations