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

    Neuronpedia

    INDEX
    Explanations

    submarines

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ဆင့်
    0.56
    uz
    0.54
     tận
    0.54
    ứ
    0.52
     compounds
    0.51
     gradients
    0.50
     cardi
    0.50
     layers
    0.49
     cleansing
    0.49
     Luz
    0.49
    POSITIVE LOGITS
    Andrew
    0.63
    审核
    0.62
    槳
    0.62
    PLOAD
    0.61
    Xbox
    0.61
    Oxford
    0.61
    Bark
    0.61
    ♏
    0.60
    🔱
    0.59
     carico
    0.59
    Act Density 0.001%

    No Known Activations