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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Importance
    0.47
    Same
    0.45
     Tử
    0.43
    Importance
    0.42
     Characteristics
    0.41
     Several
    0.41
     Specifies
    0.41
     mehrere
    0.39
     Same
    0.39
     Significance
    0.38
    POSITIVE LOGITS
     own
    1.25
     favorite
    0.93
     favourite
    0.82
     entire
    0.74
     propia
    0.74
     собстве
    0.74
     eigenes
    0.73
     efforts
    0.72
     собственных
    0.72
     chosen
    0.71
    Act Density 0.511%

    No Known Activations