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

    Neuronpedia

    INDEX
    Explanations

    cities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keep
    0.34
     be
    0.34
     limited
    0.32
     still
    0.32
     Lower
    0.32
     sandpaper
    0.31
     understand
    0.31
    เทศ
    0.30
     perfectly
    0.30
     बांटा
    0.30
    POSITIVE LOGITS
    peria
    0.45
    eningen
    0.44
    漃
    0.42
    GÁ
    0.40
    znál
    0.40
     ребен
    0.39
    nington
    0.39
    izzano
    0.39
    apabb
    0.39
     ребён
    0.39
    Act Density 0.137%

    No Known Activations