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

    Neuronpedia

    INDEX
    Explanations

    side effects, commitment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vecino
    0.45
     이때
    0.44
     convoluted
    0.43
    fler
    0.43
     poetic
    0.42
    -}$
    0.42
     be
    0.41
     his
    0.41
     zach
    0.40
     fructose
    0.39
    POSITIVE LOGITS
    ↵
    0.61
    Seasonal
    0.54
    লা
    0.54
    Doctor
    0.53
     Characteristics
    0.50
    ل
    0.50
    Multi
    0.50
    Site
    0.50
     Events
    0.49
     Predictions
    0.49
    Act Density 0.001%

    No Known Activations