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

    Neuronpedia

    INDEX
    Explanations

    North Dakota

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंध
    0.39
    పే
    0.39
     Receptor
    0.39
     *}
    0.37
    ement
    0.36
    cony
    0.36
    ੈ
    0.35
    Powell
    0.35
     мама
    0.34
     loved
    0.34
    POSITIVE LOGITS
     Bismarck
    0.61
     Fargo
    0.54
     Bremen
    0.52
     ND
    0.50
     Bremer
    0.47
    ismarck
    0.46
    ミネ
    0.41
     Hanover
    0.40
     NDR
    0.39
     لاس
    0.38
    Act Density 0.004%

    No Known Activations