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

    Neuronpedia

    INDEX
    Explanations

    front or front-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ளான
    0.41
    LS
    0.39
    Источник
    0.38
    жда
    0.38
    される
    0.38
     comprador
    0.38
    ưới
    0.37
    емым
    0.37
    เอียด
    0.36
    メタル
    0.36
    POSITIVE LOGITS
     front
    0.67
    front
    0.66
     Front
    0.64
     фрон
    0.60
    Front
    0.58
     FRONT
    0.58
    FRONT
    0.54
     porch
    0.53
    foreground
    0.52
     foreground
    0.52
    Act Density 0.010%

    No Known Activations