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

    Neuronpedia

    INDEX
    Explanations

    insurance company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     radiance
    -0.81
     हे
    -0.80
    gpl
    -0.79
    tka
    -0.77
    Servus
    -0.76
     orific
    -0.73
     Horacio
    -0.73
    леб
    -0.71
     sects
    -0.71
    tku
    -0.71
    POSITIVE LOGITS
     hablar
    0.96
     կ
    0.82
    立即
    0.73
    Regulation
    0.72
    цкая
    0.71
    nový
    0.71
     Cass
    0.70
     beziehungs
    0.70
    GIA
    0.70
     Shar
    0.68
    Act Density 0.032%

    No Known Activations