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

    Neuronpedia

    INDEX
    Explanations

    completing lists or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     befindet
    0.45
    āng
    0.43
     three
    0.43
     began
    0.43
     beginnt
    0.42
     üç
    0.42
    ının
    0.41
    is
    0.41
    țile
    0.40
    ites
    0.40
    POSITIVE LOGITS
     eficiencia
    0.57
     pengurangan
    0.51
     ahorro
    0.51
     taxas
    0.49
     lucro
    0.49
     nieve
    0.49
     preservatives
    0.48
     dehumid
    0.48
     sewerage
    0.47
     rinsing
    0.47
    Act Density 0.001%

    No Known Activations