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

    Neuronpedia

    INDEX
    Explanations

    asking for specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     improbable
    0.65
     unnoticed
    0.55
     करताना
    0.53
     aback
    0.51
    されない
    0.51
    Читати
    0.50
     a
    0.50
    শুধু
    0.49
    যখন
    0.49
    となった
    0.48
    POSITIVE LOGITS
     haue
    0.83
     belongs
    0.81
     heeft
    0.80
     najbardziej
    0.78
     possesses
    0.77
     has
    0.76
     έχει
    0.75
     makes
    0.74
     corresponds
    0.73
     would
    0.71
    Act Density 0.014%

    No Known Activations