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

    Neuronpedia

    INDEX
    Explanations

    types of people

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ے۔
    0.79
     relem
    0.76
     erab
    0.74
     rudder
    0.74
    crud
    0.72
     apa
    0.72
     проявля
    0.71
     DEA
    0.70
     све
    0.70
     IVA
    0.70
    POSITIVE LOGITS
     warriors
    0.93
     gangsters
    0.92
    PL
    0.90
     pirates
    0.90
     pilots
    0.87
     Warriors
    0.87
     gunmen
    0.85
     witches
    0.85
     hunters
    0.85
    Pixels
    0.85
    Act Density 0.000%

    No Known Activations