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

    Neuronpedia

    INDEX
    Explanations

    magnificent views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mundur
    0.42
     pont
    0.41
    ebi
    0.41
     tespit
    0.41
     prête
    0.38
     heredit
    0.38
     Très
    0.37
    यात
    0.37
     dónde
    0.36
     Samantha
    0.36
    POSITIVE LOGITS
     views
    0.42
    view
    0.40
     incomparable
    0.40
    views
    0.39
     view
    0.39
    Admin
    0.38
    watch
    0.36
     unforgettable
    0.36
    Views
    0.36
     Kettle
    0.35
    Act Density 0.002%

    No Known Activations