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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     testicule
    0.41
    qttr
    0.40
    दून
    0.40
    (""))
    0.38
     vutta
    0.38
     agarose
    0.37
     peculiarities
    0.37
    రీ
    0.36
     กี่
    0.36
     runApp
    0.36
    POSITIVE LOGITS
     Definitely
    0.71
    Definitely
    0.70
     Excellent
    0.68
    Excellent
    0.67
     Plenty
    0.64
     definitely
    0.61
    Plenty
    0.60
     Kudos
    0.60
    Overall
    0.60
     Nice
    0.59
    Act Density 0.001%

    No Known Activations