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

    Neuronpedia

    INDEX
    Explanations

    formal descriptions and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     backstory
    0.60
    ებისთვის
    0.59
    Также
    0.57
     reimag
    0.54
     buttercream
    0.51
     heartbreak
    0.50
     kiddos
    0.50
     देखील
    0.48
     badass
    0.48
     grayscale
    0.48
    POSITIVE LOGITS
     hitherto
    0.80
     constituting
    0.79
     inasmuch
    0.75
     pertaining
    0.75
     invariably
    0.71
     aforesaid
    0.70
     envisaged
    0.70
     desirous
    0.70
     comprising
    0.68
     constitute
    0.67
    Act Density 0.005%

    No Known Activations