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

    Neuronpedia

    INDEX
    Explanations

    real estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wem
    0.89
     véritable
    0.86
     Displays
    0.81
    éct
    0.80
    𝒕
    0.79
    DomainMask
    0.78
    아
    0.78
    hematic
    0.77
    циа
    0.77
    inuous
    0.77
    POSITIVE LOGITS
     world
    0.86
     mondo
    0.78
     estate
    0.75
    world
    0.71
     stoned
    0.70
    iz
    0.70
    elif
    0.70
     dogged
    0.69
     bandwidth
    0.69
     barbed
    0.67
    Act Density 0.078%

    No Known Activations