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

    Neuronpedia

    INDEX
    Explanations

    woodland and bushfire contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.80
    5
    0.62
    าย
    0.59
    sus
    0.57
    tribe
    0.56
    aman
    0.55
    was
    0.54
    diam
    0.54
     Estas
    0.54
     Queste
    0.53
    POSITIVE LOGITS
    目安
    0.55
     woodland
    0.54
    慝
    0.53
    是
    0.52
     bevel
    0.52
    ي
    0.51
    ية
    0.50
    ö
    0.49
    ك
    0.49
     även
    0.49
    Act Density 0.001%

    No Known Activations