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

    Neuronpedia

    INDEX
    Explanations

    bodies of water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icted
    0.72
    standing
    0.72
     distinction
    0.71
    tering
    0.70
     bunny
    0.66
    ST
    0.65
     fra
    0.64
    ervation
    0.64
     IPF
    0.63
     knapp
    0.62
    POSITIVE LOGITS
     приме
    0.87
     начале
    0.87
    ногда
    0.84
    ﻨ
    0.82
    localhost
    0.80
     אם
    0.79
     estableció
    0.79
     ondas
    0.77
    по
    0.76
    carouselExample
    0.76
    Act Density 0.071%

    No Known Activations