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

    Neuronpedia

    INDEX
    Explanations

    ports or gates

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANY
    0.61
     geniş
    0.61
    atakse
    0.59
    కుంట
    0.57
     넓
    0.53
    MRS
    0.53
    Garage
    0.53
    AKT
    0.53
    창
    0.53
    Dist
    0.52
    POSITIVE LOGITS
     vieron
    0.60
    ாலி
    0.59
    良かった
    0.58
     Offer
    0.57
    rion
    0.57
    銛
    0.56
     Lew
    0.56
    දී
    0.55
     northward
    0.55
     Hir
    0.55
    Act Density 0.000%

    No Known Activations